Multi-task domain adaptation method for computation offloading

Abstract

The present invention discloses a multi-task domain adaptation method for computational offloading. The method comprises: constructing an objective function based on the scenario in which the user processes the target task on their own or offloads it to an edge server for processing, obtaining multiple sets of source domain data, each set of source domain data including sample data and labels of multiple users, the labels being initial classification values ​​and initial regression values; inputting the multiple sets of source domain data into a feedforward neural network model to obtain a trained feedforward neural network model; obtaining multiple sets of target domain data, enhancing the multiple sets of target domain data to obtain multiple sets of enhanced target domain data; wherein each set of target domain data includes sample data of multiple users. The present invention solves the technical problems of the existing task offloading model in different domain environments, such as low generalization ability, high privacy risk, large computational load, and long computational time.

Description

Technical Field

[0001] The present invention relates to the field of resource computing technology, and in particular to a multi-task domain adaptation method for computing offloading. Background Art

[0002] With the rapid development of Multi-access Edge Computing (MEC) technology, its role in reducing network latency and improving computing efficiency has been widely recognized. By deploying computing resources at the edge of the network, MEC can effectively alleviate the performance bottlenecks caused by limited computing resources on mobile devices. Especially in the context of the widespread use of mobile communications and smart terminals, MEC offloads computationally intensive tasks from resource-constrained terminal devices to edge servers, thereby improving overall computing efficiency and reducing the load on terminal devices.

[0003] In the MEC environment, the task offloading problem can generally be divided into two sub-problems: task offloading decision-making and computing resource allocation. To cope with the dynamically changing network environment, swarm intelligence networks have gradually become an important means of edge computing. By integrating the collective intelligence of multiple mobile users and edge devices, edge intelligent networks achieve collaborative decision-making and resource sharing, thereby optimizing task offloading decisions in complex and changing network environments. However, due to the constant changes in the network environment, the data distribution in the target domain often differs significantly from that in the source domain, which makes it difficult for traditional task offloading methods based on mathematical models to be effectively generalized in new environments.

[0004] To improve the generalization capability of task offloading models across different domains, artificial intelligence technologies such as deep reinforcement learning (DRL) have been widely used in MEC systems in recent years. The goal is to learn optimal task offloading strategies by dynamically interacting with the wireless environment. However, traditional DRL methods have poor adaptability in the face of unpredictable disturbances and require comprehensive retraining, resulting in high application costs in new environments.

[0005] Although existing technologies have made some progress in MEC task offloading, they still have some significant shortcomings and deficiencies:

[0006] Poor adaptability: Traditional computing task offloading models usually rely on pre-trained mathematical models or neural networks for decision-making. These models overfit the source domain data during training. When the target domain data deviates significantly from the source domain, the model's generalization ability is weak, resulting in a significant decrease in inference accuracy.

[0007] Privacy issues: In MEC systems, source domain data often involves sensitive user information. Traditional methods require access to source domain data during the inference process, which may lead to user privacy leaks. Moreover, accessing source domain data also brings a large storage and computing burden.

[0008] High retraining cost: To adapt to changes in different network environments, existing technologies usually require retraining the model, which not only consumes a lot of computing resources but also takes a long time, making it difficult to meet the real-time and high-efficiency requirements of the MEC system.

[0009] Low resource utilization efficiency: Because existing models fail to effectively consider the dynamic changes in the network environment, they suffer from low resource utilization efficiency in resource allocation and task offloading decisions. This not only reduces the computing resource utilization of edge servers, but may also lead to increased task delays, affecting the user experience. Summary of the Invention

[0010] The embodiments of the present invention provide a multi-task domain adaptation method for computation offloading, so as to at least solve the technical problems of low generalization ability, high privacy risk, large computation amount and long computation time of existing task offloading models in different domain environments.

[0011] According to one aspect of an embodiment of the present invention, a multi-task domain adaptation method for computational offloading is provided. The method may include: constructing an objective function according to a scenario in which the user processes the target task by himself or offloads it to an edge server for processing; obtaining multiple sets of source domain data, each set of source domain data includes sample data and labels of multiple users, and the labels are initial classification values ​​and initial regression values; inputting the multiple sets of source domain data into a feedforward neural network model to obtain a trained feedforward neural network model; obtaining multiple sets of target domain data, enhancing the multiple sets of target domain data to obtain multiple sets of enhanced target domain data; wherein each set of target domain data includes sample data of multiple users; constructing a teacher-student model, wherein the teacher-student model includes a student model and a teacher model, and the trained feedforward neural network model is used as the teacher model and the student model respectively; inputting the enhanced first set of target domain data into the teacher model to obtain pseudo labels for the sample data of each user, wherein the pseudo labels include a first classification prediction value and a first regression prediction value; A set of target domain data is input into the student model to obtain the initial prediction value of each user's sample data, wherein the initial prediction value includes the second classification prediction value and the second regression prediction value; based on the initial prediction value and the pseudo label, a total loss value is obtained; based on the total loss value, the model parameters of the student model are updated, and iterations are repeated. When the total loss value is minimized, the model parameters of the student model with the minimum total loss value are used to update the model parameters of the teacher model, and the model parameters of the student model with the minimum total loss value are randomly restored to obtain the restored model parameters. The restored model parameters are used as the student model corresponding to the second set of target domain data, and iterations are repeated to obtain a trained student model; each set of target domain data is input into the trained target student model to obtain the target prediction value of each set of target domain data; based on the target prediction value of each set of target domain data and the target domain data corresponding to the target prediction value, the objective function is minimized to minimize the user's computing task cost.

[0012] Optionally, the loss function of the trained feedforward neural network model is expressed as:

[0013]

[0014] in, is the total loss value of the trained feedforward neural network model, is the weight of the classification loss of the trained feedforward neural network model, is the classification loss value of the trained feedforward neural network model, is the weight of the regression loss of the trained feedforward neural network model, is the regression loss value of the trained feedforward neural network model.

[0015] Optionally, the classification loss value of the trained feedforward neural network model is expressed as:

[0016]

[0017] Among them, M is the total number of source domain data groups, is one of multiple sets of source domain data, The classification prediction value of each source domain data in the multiple source domain data output by the trained feedforward neural network model, is the initial classification value of each set of source domain data in multiple sets of source domain data.

[0018] Optionally, the regression loss of the trained feedforward neural network model is expressed as:

[0019]

[0020] in, is the regression loss of the trained feedforward neural network model.

[0021] Optionally, obtaining a total loss value based on the initial prediction value and the pseudo label includes: obtaining a cross entropy loss value based on the first classification prediction value and the second classification prediction value; obtaining a mean square error loss value based on the first regression prediction value and the second regression prediction value; and obtaining a total loss value based on the cross entropy loss value and the mean square error loss value.

[0022] Optionally, the expression for obtaining the total loss value based on the cross entropy loss value and the mean square error loss value is:

[0023]

[0024] in, represents the total loss value, is the cross entropy loss value, is the mean square error loss value, is the first hyperparameter, is the second hyperparameter.

[0025] Optionally, the model parameters of the student model when the total loss value is minimized are randomly restored, and the expression for the restored model parameters is obtained as follows:

[0026]

[0027] in, are the restored model parameters, is the mask tensor, are the model parameters of the feedforward neural network model, represents the convolution operation, The model parameters of the student model when the total loss value is minimized.

[0028] Beneficial effects of the present invention:

[0029] (1) By introducing the teacher-student architecture, there is no need to access source domain data during the inference phase. This not only effectively protects user privacy and avoids the leakage of sensitive information, but also reduces the storage and computing burden, making the system more lightweight and secure. This architectural design reduces dependence on source domain data, thereby significantly reducing data transmission and storage overhead.

[0030] (2) By adopting a multi-task learning framework, the present invention can simultaneously handle task offloading decisions and computing resource allocation problems; compared with the traditional single-task model, this framework improves the resource utilization efficiency of the system, enabling the edge server to more reasonably allocate computing resources in a dynamically changing environment, thereby reducing task delays and improving user experience; at the same time, the joint training of classification and regression tasks enables the model to better cope with complex environments and improve adaptability.

[0031] (3) The student model is continuously updated during the inference phase through a dynamic adaptive adjustment mechanism to adapt to changes in the target domain data. This mechanism reduces the reliance on comprehensive retraining, enabling the model to adapt to new environments more quickly, improving generalization capabilities and computational efficiency. This means that the present invention can be rapidly deployed and adjusted in different network environments, reducing the cost of system maintenance and updates.

[0032] (4) By combining the cross entropy loss of the classification task and the mean square error loss of the regression task, an optimized weighted loss function is designed, which enables the model to strike a balance between the accuracy of task offloading decisions and resource allocation; by reasonably adjusting the weights, the model can take into account multiple objectives at the same time during the optimization process, improving the overall performance, thereby making edge computing perform better in multi-task scenarios.

[0033] (5) By introducing a random recovery mechanism into the student model, the present invention effectively prevents the catastrophic forgetting problem that may occur during the long-term adaptive process. This mechanism partially restores the parameters of the student model to their initial state, ensuring that the model can still maintain its ability to understand the original task during the long-term learning process, thereby achieving low-cost continuous learning. This design not only improves the adaptability of the model, but also significantly reduces the cost of retraining, allowing the system to remain efficient and stable during long-term operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0035] Figure 1is a flowchart of a multi-task domain adaptation method for computation offloading according to an embodiment of the present invention;

[0036] Figure 2 4 is a framework diagram of a multi-task domain adaptation method for computation offloading according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or inherent to these processes, methods, products or devices.

[0039] Example 1

[0040] According to an embodiment of the present invention, a multi-task domain adaptation method for computational offloading is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system containing at least one set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] Figure 1 is a flowchart of a multi-task domain adaptation method for computation offloading according to an embodiment of the present invention. Figure 1 As shown, the method may include the following steps:

[0042] Step S101 : constructing an objective function according to a scenario in which a user processes a target task on their own or offloads it to an edge server for processing.

[0043] In the technical solution provided in step S101 of the present invention, in a single-server multi-user MEC system, it is assumed that mobile users, i.e. , the N-dimensional offloading decision vector of mobile users to the edge server (Mobile Edge Server, referred to as MES) is expressed as , respectively Indicates that the user offloads the task to the edge server. Indicates that the user processes tasks locally, and the N-dimensional vector of MES computing resource allocation is , and guarantee , that is, MES allocates computing resources to users who need resources, and the computing resources allocated to all users do not exceed the computing resources of MES itself.

[0044] set up Represents a user The CPU cycle frequency, Indicates processing tasks The required CPU cycle frequency, Indicates The total cost of local processing on Indicates energy efficiency parameters that mainly depend on the hardware chip architecture. Indicates emphasis on computing latency and power consumption; local computing The weighted cost calculation method is:

[0045]

[0046] set up Indicate to upload The data size, Assign to user for MES computing resources, express After being processed by the edge server, the size of the processing result returned to the user, express from The data rate achieved by wireless uplink to MES, express From MES to The data rate achieved by wireless downlink, for The power consumption uploaded from the user to the edge server, Execute for edge servers Power consumption, The power consumption of the edge server when it returns the processing result to the user. The weighted cost calculation method for unloading to MES is:

[0047]

[0048] The total cost of the MEC system can be defined as the weighted sum of the costs of all mobile users:

[0049]

[0050] The computation offloading problem is formulated as a joint optimization problem of offloading decision and computational resource allocation, aiming to minimize the overall cost of the system. Under the fluctuation conditions of the network and the constraints of computational resources, the offloading decision and computational resource allocation are formulated as a mixed integer nonlinear programming problem. The joint offloading and computational resource allocation is formulated as a weighted sum cost minimization problem, i.e., the objective function is: .

[0051] Step S102 : Acquire multiple groups of source domain data, each group of source domain data includes sample data and labels of multiple users, where the labels are initial classification values ​​and initial regression values.

[0052] In the technical solution provided in step S102 of the present invention, for multiple sets of source domain data, first, user input features, such as data volume, computing cycle, local computing frequency, and channel gain, are randomly generated according to a set distribution (e.g., a normal distribution). The optimization tool GEKKO is then used to construct an offloading decision and resource allocation problem, with the goal of minimizing total costs (including local computing, transmission, and server computing costs) while satisfying latency constraints. Based on the optimization results, each user's offloading decision and resource allocation ratio are then generated as target variables. Finally, the generated input features and optimization results are saved as a tabular data file for machine learning model training, and the configuration parameters of the generated data are recorded for reproduction.

[0053] Step S103: input multiple sets of source domain data into the feedforward neural network model to obtain a trained feedforward neural network model.

[0054] In the technical solution provided in the above step S103 of the present invention, the feedforward neural network model is trained on multiple sets of source domain data to obtain a trained feedforward neural network model.

[0055] Step S104 , acquiring multiple sets of target domain data, and enhancing the multiple sets of target domain data to obtain multiple sets of enhanced target domain data; wherein each set of target domain data includes sample data of multiple users.

[0056] In the technical solution provided in the above step S104 of the present invention, multiple sets of target domain data: input features of nodes, such as data volume, calculation cycle, local calculation frequency, channel gain, etc., are randomly generated according to a distribution different from that set in the source domain (such as a normal distribution), and the generated input features are saved as a tabular data file for use in machine learning.

[0057] Step S105: construct a teacher-student model, wherein the teacher-student model includes a student model and a teacher model, and the trained feedforward neural network model is used as the teacher model and the student model respectively.

[0058] In the technical solution provided in the above step S105 of the present invention, Figure 2 is a framework diagram of a multi-task domain adaptation method for computation offloading according to an embodiment of the present invention, such as Figure 2 The teacher model and student model in .

[0059] Step S106: input the enhanced first set of target domain data into the teacher model to obtain pseudo labels for each user's sample data, wherein the pseudo labels include a first classification prediction value and a first regression prediction value.

[0060] In the technical solution provided in step S106 of the present invention, if Figure 2 As shown in the figure, multiple sets of target domain data are enhanced, and the first set of enhanced target domain data is input into the teacher model to obtain the pseudo labels of each user's sample data, that is, the classification prediction value (first classification prediction value) and regression prediction value (first regression prediction value) behind the teacher model.

[0061] Step S107 : input the first set of target domain data into the student model to obtain an initial prediction value of each user's sample data, wherein the initial prediction value includes a second classification prediction value and a second regression prediction value.

[0062] In the technical solution provided in step S107 of the present invention, if Figure 2 As shown, the student model processes the first set of target domain data to obtain the initial prediction value of each user's sample data, which is Figure 2 The classification prediction value (second classification prediction value) and regression prediction value (second regression prediction value) behind the middle school student model.

[0063] Step S108: Obtain a total loss value based on the initial prediction value and the pseudo label.

[0064] In the technical solution provided in the above step S108 of the present invention, the initial prediction value and the pseudo label are calculated to obtain a total loss value.

[0065] Step S109: Based on the total loss value, update the model parameters of the student model, repeat the iteration, and when the total loss value is minimized, use the model parameters of the student model when the total loss value is minimized to update the model parameters of the teacher model. Randomly restore the model parameters of the student model when the total loss value is minimized to obtain the restored model parameters. The restored model parameters are used as the student model corresponding to the second set of target domain data, and the iteration is repeated to obtain the trained student model.

[0066] In the technical solution provided in step S109 of the present invention, if Figure 2 As shown in , based on the total loss value, the model parameters of the student model are updated, the total loss value is back-propagated, and the gradient is calculated. When the total loss value is minimized, the model parameters of the student model at the minimum total loss value are used to update the model parameters of the teacher model. The model parameters of the student model at the minimum total loss value are randomly restored to obtain the restored model parameters. The restored model parameters are used as the student model corresponding to the second set of target domain data. When all epoch training is completed, the trained student model is obtained, as shown in Figure 2 As shown, the model parameters of the student model when the total loss value is minimized are used to update the model parameters of the teacher model. This is the process of updating the model parameters of the teacher model using the model parameters of the student model when the total loss value is minimized without random recovery.

[0067] The expression for updating the model parameters of the teacher model with the model parameters of the student model when the total loss value is minimized is:

[0068]

[0069] in, for The model parameters of the teacher model at the time step, that is, the model parameters of the updated teacher model, It is used to represent a coefficient that controls the proportion of weights provided to the teacher model during the averaging process. for The model parameters of the teacher model at the time step, that is, the model parameters of the teacher model that have not been updated, for The model parameters of the student model at this time step, that is, the model parameters of the student model when the total loss value is minimized.

[0070] Step S110 , input each set of target domain data into the trained target student model to obtain a target prediction value for each set of target domain data.

[0071] In the technical solution provided by the above step S110 of the present invention, each set of target domain data is input into the trained target student model to obtain the target prediction value of each set of target domain data.

[0072] Step S111 , based on the target prediction value of each set of target domain data and the target domain data corresponding to the target prediction value, minimize the objective function to minimize the user's computing task cost.

[0073] In the technical solution provided by step S111 of the present invention, the target prediction value of each set of target domain data and the target domain data corresponding to the target prediction value obtained in step S110 are substituted into In the process of solving the problem, the minimum cost of the user's computing task is obtained.

[0074] The above method of this embodiment is further introduced below.

[0075] As an optional embodiment, in step S103, the loss function of the trained feedforward neural network model is expressed as:

[0076]

[0077] in, is the total loss value of the trained feedforward neural network model, is the weight of the classification loss of the trained feedforward neural network model, is the classification loss value of the trained feedforward neural network model, is the weight of the regression loss of the trained feedforward neural network model, is the regression loss value of the trained feedforward neural network model.

[0078] As an optional embodiment, the classification loss value of the trained feedforward neural network model is expressed as:

[0079]

[0080] Among them, M is the total number of source domain data groups, is one of multiple sets of source domain data, The classification prediction value of each source domain data in the multiple source domain data output by the trained feedforward neural network model, is the initial classification value of each set of source domain data in multiple sets of source domain data.

[0081] As an optional embodiment, the regression loss of the trained feedforward neural network model is expressed as:

[0082]

[0083] in, is the regression loss of the trained feedforward neural network model.

[0084] As an optional embodiment, step S108, the total loss value is obtained based on the initial prediction value and the pseudo label, including: obtaining a cross entropy loss value based on the first classification prediction value and the second classification prediction value; obtaining a mean square error loss value based on the first regression prediction value and the second regression prediction value; obtaining a total loss value based on the cross entropy loss value and the mean square error loss value.

[0085] In this embodiment, the first classification prediction value and the second classification prediction value are calculated to obtain a cross entropy loss value; the first regression prediction value and the second regression prediction value are calculated to obtain a mean square error loss value; the cross entropy loss value and the mean square error loss value are calculated to obtain a total loss value.

[0086] As an optional embodiment, the expression for obtaining the total loss value based on the cross entropy loss value and the mean square error loss value is:

[0087]

[0088] in, represents the total loss value, is the cross entropy loss value, is the mean square error loss value, is the first hyperparameter, is the second hyperparameter.

[0089] In this embodiment, the cross entropy loss value, the mean square error loss value, the first hyperparameter, and the second hyperparameter are calculated to obtain a total loss value.

[0090] Among them, the expression of the cross entropy loss value is:

[0091]

[0092] in, is the first classification prediction value, that is, the first classification prediction value predicted by the student model for the sample data of the i-th user, is the second classification prediction value, that is, the second classification prediction value predicted by the teacher model for the sample data of the i-th user.

[0093] The expression of the mean square error loss value is:

[0094]

[0095] in, is the first regression prediction value, that is, the first regression prediction value predicted by the student model for the sample data of the i-th user, is the second regression prediction value, that is, the second regression prediction value predicted by the teacher model for the sample data of the i-th user.

[0096] As an optional embodiment, in step S109, the model parameters of the student model when the total loss value is minimized are randomly restored, and the expression of the restored model parameters is obtained as follows:

[0097]

[0098] in, are the restored model parameters, is the mask tensor, are the model parameters of the feedforward neural network model, represents the convolution operation, The model parameters of the student model when the total loss value is minimized.

[0099] In this embodiment, the mask tensor By a probability The Bernoulli distribution is generated, that is, .

[0100] In an embodiment of the present invention, an objective function is constructed according to a scenario in which a user processes a target task by himself or offloads it to an edge server for processing; multiple sets of source domain data are obtained, each set of source domain data includes sample data and labels of multiple users, and the labels are initial classification values ​​and initial regression values; the multiple sets of source domain data are input into a feedforward neural network model to obtain a trained feedforward neural network model; multiple sets of target domain data are obtained, and the multiple sets of target domain data are enhanced to obtain multiple sets of enhanced target domain data; wherein each set of target domain data includes sample data of multiple users; a teacher-student model is constructed, wherein the teacher-student model includes a student model and a teacher model, and The trained feedforward neural network model is used as the teacher model and the student model respectively; the enhanced first set of target domain data is input into the teacher model to obtain the pseudo label of each user's sample data, wherein the pseudo label includes the first classification prediction value and the first regression prediction value; the first set of target domain data is input into the student model to obtain the initial prediction value of each user's sample data, wherein the initial prediction value includes the second classification prediction value and the second regression prediction value; based on the initial prediction value and the pseudo label, the total loss value is obtained; based on the total loss value, the model parameters of the student model are updated, and the iteration is repeated. When the total loss value is minimized, the model parameters of the student model with the minimum total loss value are used. The model parameters of the teacher model are updated randomly, and the model parameters of the student model when the total loss value is minimized are randomly restored to obtain the restored model parameters. The restored model parameters are used as the student model corresponding to the second set of target domain data, and repeated iterations are performed to obtain the trained student model; each set of target domain data is input into the trained target student model to obtain the target prediction value of each set of target domain data; based on the target prediction value of each set of target domain data and the target domain data corresponding to the target prediction value, the objective function is minimized to minimize the user's computing task cost, which solves the problems of low generalization ability, high privacy risk, large computational complexity and computing complexity of the existing task offloading model in different domain environments. In order to solve the technical problem of long computing time, we have achieved efficient task offloading and computing resource allocation through a teacher-student architecture, a multi-task learning framework, dynamic adaptive adjustment, optimized loss function design, and low-cost continuous learning. In the inference stage, the teacher model guides the student model to achieve continuous adaptation without the need for source domain data, protecting user privacy and reducing computing costs. Multi-task learning integrates task offloading decisions and resource allocation, and jointly optimizes to improve adaptability. Dynamic adjustment enables the student model to adapt to changes in the target domain, and the optimized weighted loss function takes into account both classification and regression performance. In addition, the random recovery mechanism prevents catastrophic forgetting in long-term self-learning.

[0101] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0102] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0104] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected to achieve the purpose of the present embodiment according to actual needs.

[0105] In addition, the functional units in various embodiments of the present invention may be integrated into a first processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0106] The above are only preferred embodiments of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A multi-task domain adaptation method for computation offloading, characterized by: include: Construct an objective function based on the scenario where the user processes the target task themselves or offloads it to an edge server. Obtain multiple sets of source domain data, each set of source domain data includes sample data and labels of multiple users, where the labels are initial classification values ​​and initial regression values; Input multiple sets of source domain data into the feedforward neural network model to obtain a trained feedforward neural network model; Acquire multiple sets of target domain data, and enhance the multiple sets of target domain data to obtain multiple sets of enhanced target domain data; wherein each set of target domain data includes sample data of multiple users; Construct a teacher-student model, where the teacher-student model includes a student model and a teacher model, and the trained feedforward neural network model is used as the teacher model and the student model respectively; Input the enhanced first set of target domain data into the teacher model to obtain pseudo labels for each user's sample data, where the pseudo labels include a first classification prediction value and a first regression prediction value; Inputting the first set of target domain data into the student model to obtain an initial prediction value of each user's sample data, wherein the initial prediction value includes a second classification prediction value and a second regression prediction value; Based on the initial prediction value and pseudo label, the total loss value is obtained; Based on the total loss value, the model parameters of the student model are updated, and the iteration is repeated. When the total loss value is minimized, the model parameters of the student model at the minimum total loss value are used to update the model parameters of the teacher model. The model parameters of the student model at the minimum total loss value are randomly restored to obtain the restored model parameters. The restored model parameters are used as the student model corresponding to the second set of target domain data, and the iteration is repeated to obtain the trained student model. Input each set of target domain data into the trained target student model to obtain the target prediction value of each set of target domain data; Based on the target prediction value of each set of target domain data and the target domain data corresponding to the target prediction value, the objective function is minimized to minimize the user's computing task cost.

2. The method according to claim 1, characterized in that The loss function of the trained feedforward neural network model is expressed as: in, is the total loss value of the trained feedforward neural network model, is the weight of the classification loss of the trained feedforward neural network model, is the classification loss value of the trained feedforward neural network model, is the weight of the regression loss of the trained feedforward neural network model, is the regression loss value of the trained feedforward neural network model.

3. The method according to claim 2, characterized in that The expression of the classification loss value of the trained feedforward neural network model is: Among them, M is the total number of source domain data groups, is one of multiple sets of source domain data, The classification prediction value of each source domain data in the multiple source domain data output by the trained feedforward neural network model, is the initial classification value of each set of source domain data in multiple sets of source domain data.

4. The method according to claim 3, characterized in that The regression loss expression of the trained feedforward neural network model is: in, is the regression loss of the trained feedforward neural network model.

5. The method according to claim 1, wherein Based on the initial prediction value and pseudo label, the total loss value is obtained, including: Based on the first classification prediction value and the second classification prediction value, the cross entropy loss value is obtained; Obtain a mean square error loss value based on the first regression prediction value and the second regression prediction value; Based on the cross entropy loss value and the mean square error loss value, the total loss value is obtained.

6. The method according to claim 5, characterized in that The expression of the total loss value based on the cross entropy loss value and the mean square error loss value is: in, represents the total loss value, is the cross entropy loss value, is the mean square error loss value, is the first hyperparameter, is the second hyperparameter.

7. The method according to claim 1, characterized in that The model parameters of the student model when the total loss value is minimized by random recovery are obtained, and the expression of the recovered model parameters is: in, are the restored model parameters, is the mask tensor, are the model parameters of the feedforward neural network model, represents the convolution operation, The model parameters of the student model when the total loss value is minimized.

8. A computer system, characterized in that include: One or more processors, and a computer-readable storage medium for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are enabled to implement the method of claim 1.

9. A computer-readable storage medium, characterized in that Computer-executable instructions are stored, and when the instructions are executed, they are used to implement the method of claim 1.

10. A computer program product, characterized in that The invention comprises computer executable instructions, which are used to implement the method of claim 1 when the instructions are executed.

Images