Adaptive Shortcut Debiasing for Online Continual Learning
We propose a novel framework DropTop that suppresses the shortcut bias in online continual learning (OCL) while being adaptive to the varying degree of the shortcut bias incurred by continuously changing environment. By the observed high-attention property of the shortcut bias, highly-activated features are considered candidates for debiasing. More importantly, resolving the limitation of the online environment where prior knowledge and auxiliary data are not ready, two novel techniques -- feature map fusion and adaptive intensity shifting -- enable us to automatically determine the appropriate level and proportion of the candidate shortcut features to be dropped. Extensive experiments on five benchmark datasets demonstrate that, when combined with various OCL algorithms, DropTop increases the average accuracy by up to 10.4% and decreases the forgetting by up to 63.2%.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningSimilar Papers 제목 키워드 기반
Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features
Machine learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, such as hiring, banking,…
FairnessOnline Prototype Learning for Online Continual Learning
Online continual learning (CL) studies the problem of learning continuously from a single-pass data stream while adapting to new data and mitigating catastrophic forgetting. Recently, by storing a small subset of old dat…
Continual LearningKnowledge DistillationMedical Image Debiasing by Learning Adaptive Agreement from a Biased Council
Deep learning could be prone to learning shortcuts raised by dataset bias and result in inaccurate, unreliable, and unfair models, which impedes its adoption in real-world clinical applications. Despite its significance,…
Attributeimage-classificationImage ClassificationMedical Image ClassificationRobust Collaborative Filtering to Popularity Distribution Shift
In leading collaborative filtering (CF) models, representations of users and items are prone to learn popularity bias in the training data as shortcuts. The popularity shortcut tricks are good for in-distribution (ID) pe…
Collaborative FilteringDiagnosing Shortcut-Induced Rigidity in Continual Learning: The Einstellung Rigidity Index (ERI)
Deep neural networks frequently exploit shortcut features, defined as incidental correlations between inputs and labels without causal meaning. Shortcut features undermine robustness and reduce reliability under distribu…
Continual Learning