Evolution-Inspired Sample Competition for Deep Neural Network Optimization

2026-04-14

AI Summary

This work addresses the limitations of conventional deep learning training paradigms, which adopt a uniform approach that overlooks sample heterogeneity and is thus vulnerable to class imbalance, insufficient learning of hard examples, and noise interference. Inspired by natural evolution, the authors propose Natural Selection (NS), a novel optimization method that introduces evolutionary competition into deep learning for the first time. NS dynamically computes a natural selection score for each sample by constructing composite images and analyzing intra-batch prediction consistency, then adaptively reweights the loss accordingly. The method requires no task-specific assumptions and is compatible with mainstream network architectures. Evaluated across twelve public datasets and four image classification tasks, NS consistently outperforms baseline methods, demonstrating strong generalization capability and practical utility.

Technology Category

• Machine Learning: Evolutionary Learning
• Search and Optimization: Evolutionary Computation
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Conventional deep network training generally optimizes all samples under a largely uniform learning paradigm, without explicitly modeling the heterogeneous competition among them. Such an oversimplified treatment can lead to several well-known issues, including bias under class imbalance, insufficient learning of hard samples, and the erroneous reinforcement of noisy samples. In this work, we present \textit{Natural Selection} (NS), a novel evolution-inspired optimization method that explicitly incorporates competitive interactions into deep network training. Unlike conventional sample reweighting strategies that rely mainly on predefined heuristics or static criteria, NS estimates the competitive status of each sample in a group-wise context and uses it to adaptively regulate its training contribution. Specifically, NS first assembles multiple samples into a composite image and rescales it to the original input size for model inference. Based on the resulting predictions, a natural selection score is computed for each sample to characterize its relative competitive variation within the constructed group. These scores are then used to dynamically reweight the sample-wise loss, thereby introducing an explicit competition-driven mechanism into the optimization process. In this way, NS provides a simple yet effective means of moving beyond uniform sample treatment and enables more adaptive and balanced model optimization. Extensive experiments on 12 public datasets across four image classification tasks demonstrate the effectiveness of the proposed method. Moreover, NS is compatible with diverse network architectures and does not depend on task-specific assumptions, indicating its strong generality and practical potential. The code will be made publicly available.

Problem

• class imbalance
• hard samples
• noisy samples
• sample competition
• uniform learning paradigm

Innovation

• Natural Selection
• Sample Competition
• Dynamic Reweighting
• Evolution-Inspired Optimization
• Hard Sample Mining