Neural Network Co-Training for Architecture Search

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current neural architecture search methods incur high computing costs due to the need to train each sampled architecture from scratch, even when using super-networks and sub-networks, which is inefficient and environmentally costly.

Innovation Solution

The method involves co-training a full-sized network and multiple sub-networks in parallel using supervised co-training iterations, where the full-sized network is maximized with respect to ground truth labels, and sub-networks are trained based on the output of the full-sized network, reducing the number of sampled networks and training time through upper-attentive sampling and in-place distillation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If each sampled architecture is trained from scratch, then the optimal neural network architecture can be found, but the computing cost increases significantly

Engineering Contradiction:
Improvearchitecture optimization accuracyVSAvoidcomputing cost
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the training process by dividing architectures into a full-sized network and multiple sub-networks with different FLOPs. Each sub-network is trained independently with its own optimizer and loss function, allowing parallel training without requiring to train each architecture from scratch separately. This segmentation enables efficient exploration of architecture space while reducing redundant computation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates a universal training framework that can handle multiple architectures simultaneously. The full-sized network and sub-networks share the same backbone structure and can be trained in parallel using the same infrastructure. This multi-functionality allows the system to optimize multiple architectures with different hardware constraints in a single training run, significantly reducing computing costs.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Productivity

If multiple architectures are trained in parallel, then the training time is reduced, but the system complexity increases

Engineering Contradiction:
Improvetraining efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the network into a full-sized network and multiple sub-networks, each with distinct FLOPs and training objectives. This segmentation allows independent optimization of each network while maintaining a unified training framework. The modular structure makes it easier to manage complexity compared to training completely independent architectures.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a teacher-student framework where the full-sized network acts as a teacher and sub-networks act as students. This intermediary relationship provides a structured way to manage parallel training, with the teacher network guiding the training of student networks through knowledge distillation. This mediator structure simplifies the coordination of multiple parallel training processes.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Use of energy by moving object

If sub-networks share weights with the super-network, then the training cost is reduced, but the ability to optimize for specific hardware constraints is limited

Engineering Contradiction:
Improvetraining costVSAvoidhardware constraint optimization
Core Design Contradiction:
Use of energy by moving objectVSAdaptability or versatility

Solution Approach 1:

The patent segments the weight sharing strategy by allowing partial weight sharing between the full-sized network and sub-networks. Instead of complete weight sharing, each sub-network has its own trainable parameters while sharing the backbone structure. This enables both cost efficiency through shared initialization and adaptability through independent optimization for specific hardware constraints.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by allowing different sub-networks to have different levels of weight independence based on their specific hardware constraints. Sub-networks targeting different FLOPs can have different degrees of parameter sharing, enabling localized optimization for specific deployment scenarios while maintaining overall training efficiency.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4163835A1System and method for training a neural network under performance and hardware constraints
Publication Date: 2023.04.12 SAMSUNG ELECTRONICS CO LTD
  • EP4163835A1 patent drawingFigure 1
  • EP4163835A1 patent drawingFigure 2
  • EP4163835A1 patent drawingFigure 3

AI summary

A system and method for training a neural network. In some embodiments the method includes training a full-sized network and a plurality of sub-networks, the training including performing a plurality of iterations of supervised co-training, the performing of each iteration including co-training the full-sized network and a subset of the plurality of sub-networks.