paper-with-me

홈 › Papers

Revisiting Softmax Masking: Stop Gradient for Enhancing Stability in Replay-based Continual Learning

2023-09-26 · Hoyong Kim, Minchan Kwon, Kangil Kim

In replay-based methods for continual learning, replaying input samples in episodic memory has shown its effectiveness in alleviating catastrophic forgetting. However, the potential key factor of cross-entropy loss with softmax in causing catastrophic forgetting has been underexplored. In this paper, we analyze the effect of softmax and revisit softmax masking with negative infinity to shed light on its ability to mitigate catastrophic forgetting. Based on the analyses, it is found that negative infinity masked softmax is not always compatible with dark knowledge. To improve the compatibility, we propose a general masked softmax that controls the stability by adjusting the gradient scale to old and new classes. We demonstrate that utilizing our method on other replay-based methods results in better performance, primarily by enhancing model stability in continual learning benchmarks, even when the buffer size is set to an extremely small value.

📄 PDF Abstract BibTeX arXiv:2309.14808

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningIncremental Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Overcoming Valid Action Suppression in Unmasked Policy Gradient Algorithms

2026-03-10 · Renos Zabounidis, Roy Siegelmann, Mohamad Qadri, Woojun Kim 외 arxiv

In reinforcement learning environments with state-dependent action validity, action masking consistently outperforms penalty-based handling of invalid actions, yet existing theory only shows that masking preserves the po…

Reinforcement Learning

Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods

2023-10-04 · Sara Klein, Simon Weissmann, Leif Döring

Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In finite-time horizons such problems are relevant for instance for optimal stopping or specific suppl…

Decision MakingPolicy Gradient MethodsSequential Decision Making

Revisiting the Gumbel-Softmax in MADDPG

2023-02-23 · Callum Rhys Tilbury, Filippos Christianos, Stefano V. Albrecht

MADDPG is an algorithm in multi-agent reinforcement learning (MARL) that extends the popular single-agent method, DDPG, to multi-agent scenarios. Importantly, DDPG is an algorithm designed for continuous action spaces, w…

BenchmarkingMulti-agent Reinforcement Learning

Revisiting Role of Autoencoders in Adversarial Settings

2020-05-21 · Byeong Cheon Kim, Jung Uk Kim, Hakmin Lee, Yong Man Ro

To combat against adversarial attacks, autoencoder structure is widely used to perform denoising which is regarded as gradient masking. In this paper, we revisit the role of autoencoders in adversarial settings. Through …

Adversarial DefenseAdversarial RobustnessDenoising

Extreme Classification via Adversarial Softmax Approximation

2020-02-15 · ICLR 2020 1 · Robert Bamler, Stephan Mandt

Training a classifier over a large number of classes, known as 'extreme classification', has become a topic of major interest with applications in technology, science, and e-commerce. Traditional softmax regression induc…

ClassificationGeneral Classification