paper-with-me

홈 › Papers

Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?

2026-05-15 · Mohammad Ali Vahedifar, Abhisek Ray, Qi Zhang arxiv

Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, neural networks suffer from catastrophic forgetting, where learning new tasks degrades performance on earlier ones. We address this problem with Shapley Neuron Valuation (SNV), a principled framework that quantifies Neuron importance in continual learning, grounded in cooperative game theory. SNV selectively freezes important Neurons while keeping others plastic, enabling buffer-free continual learning without expanding architecture. Experiments on ImageNet-1k show that SNV consistently outperforms existing buffer-free methods. In particular, SNV improves accuracy by +2.88% in the class incremental learning and +6.46% in the task incremental learning scenarios compared to the second baseline.

📄 PDF Abstract BibTeX arXiv:2605.15877

Code (0)

등록된 구현이 없습니다.

Tasks

Class Incremental LearningContinual Learning

Similar Papers 제목 키워드 기반

Neuron Shapley: Discovering the Responsible Neurons

2020-02-23 · NeurIPS 2020 12 · Amirata Ghorbani, James Zou

We develop Neuron Shapley as a new framework to quantify the contribution of individual neurons to the prediction and performance of a deep network. By accounting for interactions across neurons, Neuron Shapley is more e…

Prediction

Attention Flows are Shapley Value Explanations

2021-05-31 · ACL 2021 5 · Kawin Ethayarajh, Dan Jurafsky

Shapley Values, a solution to the credit assignment problem in cooperative game theory, are a popular type of explanation in machine learning, having been used to explain the importance of features, embeddings, and even …

Few-shot Backdoor Defense Using Shapley Estimation

2021-12-30 · CVPR 2022 1 · Jiyang Guan, Zhuozhuo Tu, Ran He, DaCheng Tao

Deep neural networks have achieved impressive performance in a variety of tasks over the last decade, such as autonomous driving, face recognition, and medical diagnosis. However, prior works show that deep neural networ…

Autonomous Drivingbackdoor defenseFace RecognitionMedical Diagnosis

Analysing Neural Network Topologies: a Game Theoretic Approach

2019-04-17 · Julian Stier, Gabriele Gianini, Michael Granitzer, Konstantin Ziegler

Artificial Neural Networks have shown impressive success in very different application cases. Choosing a proper network architecture is a critical decision for a network's success, usually done in a manual manner. As a s…

Network Pruning

Similarity-based context aware continual learning for spiking neural networks

2024-10-28 · Bing Han, Feifei Zhao, Yang Li, Qingqun Kong 외

Biological brains have the capability to adaptively coordinate relevant neuronal populations based on the task context to learn continuously changing tasks in real-world environments. However, existing spiking neural net…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning