Neural Network Parameter Compression With Adaptive Quantization Steps

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing neural networks face challenges in achieving high compression of parameter data due to varying optimal weight values, leading to inconsistent compression sizes.

Innovation Solution

A data processing device and method that includes a compression controlling unit to determine quantization steps on a node-by-node or kernel-by-kernel basis, encoding network configuration information and quantization information to generate compressed data, allowing for high compression of parameter data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If scalar-quantizing and encoding edge weights is used, then data size of edge weights is compressed, but high compression of parameter data cannot be achieved due to variations in compression size

Engineering Contradiction:
Improvedata size of parameter dataVSAvoidcompression consistency
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The patent applies local quality by determining quantization steps on a node-by-node or kernel-by-kernel basis rather than using a uniform quantization step for all parameters. This allows different regions of the neural network to have different quantization characteristics optimized for their specific properties, thereby achieving consistent high compression while maintaining accuracy.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent implements dynamics by making the quantization steps adaptive and variable rather than fixed. The compression controlling unit dynamically determines appropriate quantization steps for each node or kernel based on local characteristics, enabling the compression scheme to adapt to varying parameter distributions and achieve reliable high compression ratios.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If optimal weight values vary depending on network training results, then neural network performance is optimized, but compression size becomes inconsistent

Engineering Contradiction:
Improveweight value accuracyVSAvoidcompression size
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The patent changes the parameter of quantization step from a fixed global value to variable local values determined for each node or kernel. This parameter change allows the compression scheme to accommodate variations in optimal weight values while maintaining both accuracy and consistent compression size by adapting the quantization granularity to local needs.

Inventive Principle:
Principle #35Parameter changes

3Quantity of substance

If quantization steps are changed on a node-by-node or kernel-by-kernel basis, then high compression is achieved, but quantization information to be encoded increases

Engineering Contradiction:
Improvecompression ratio of parameter dataVSAvoidquantization information data size
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent applies merging by combining multiple quantization step values into a single quantization information structure that can be efficiently encoded. The encoding unit encodes both the network configuration information and the quantization information together, reducing overall complexity while maintaining the ability to achieve high compression through localized quantization.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3651069B1Data processing device, data processing method, and compressed data
Publication Date: 2025.10.15 MITSUBISHI ELECTRIC CORP
  • EP3651069B1 patent drawingFigure 1~2
  • EP3651069B1 patent drawingFigure 3A~4
  • EP3651069B1 patent drawingFigure 5

AI summary

A data processing unit (101) processes input data using a neural network. A compression controlling unit (102) generates quantization information that defines quantization steps. An encoding unit (103) encodes network configuration information including parameter data which is quantized using the quantization steps determined by the compression controlling unit (102), and the quantization information, to generate compressed data.