paper-with-me

Papers

Continual Feature Selection: Spurious Features in Continual Learning

2022-03-02 · Timothée Lesort

Continual Learning (CL) is the research field addressing learning without forgetting when the data distribution is not static. This paper studies spurious features' influence on continual learning algorithms. We show that continual learning algorithms solve tasks by selecting features that are not generalizable. Our experiments highlight that continual learning algorithms face two related problems: (1) spurious features and (2) local spurious features. The first one is due to a covariate shift between training and testing data, while the second is due to the limited access to data at each training step. We study (1) through a consistent set of continual learning experiments varying spurious correlation amount and data distribution support. We show that (2) is a major cause of performance decrease in continual learning along with catastrophic forgetting. This paper presents a different way of understanding performance decrease in continual learning by highlighting the influence of (local) spurious features in algorithms capabilities.

📄 PDF Abstract BibTeX arXiv:2203.01012

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learningfeature selection

Similar Papers 제목 키워드 기반

Learning Causal Models Online

2020-06-12 · Khurram Javed, Martha White, Yoshua Bengio

Predictive models -- learned from observational data not covering the complete data distribution -- can rely on spurious correlations in the data for making predictions. These correlations make the models brittle and hin…

Continual Learning

Selective Attention-based Modulation for Continual Learning

2024-03-29 · Giovanni Bellitto, Federica Proietto Salanitri, Matteo Pennisi, Matteo Boschini 외

We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting. Inspired by neurophysiological evidence that the primary visual co…

Continual LearningSaliency Prediction

Where is the Truth? The Risk of Getting Confounded in a Continual World

2024-02-09 · Florian Peter Busch, Roshni Kamath, Rupert Mitchell, Wolfgang Stammer 외

A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In this work, we show that, in a continual learning setting where confounders may vary in time across…

Continual Learningvalid

Vector Quantization Prompting for Continual Learning

2024-10-27 · Li Jiao, Qiuxia Lai, Yu Li, Qiang Xu

Continual learning requires to overcome catastrophic forgetting when training a single model on a sequence of tasks. Recent top-performing approaches are prompt-based methods that utilize a set of learnable parameters (i…

Continual LearningQuantization

Studying Generalization on Memory-Based Methods in Continual Learning

2023-06-16 · Felipe del Rio, Julio Hurtado, Cristian Buc, Alvaro Soto 외

One of the objectives of Continual Learning is to learn new concepts continually over a stream of experiences and at the same time avoid catastrophic forgetting. To mitigate complete knowledge overwriting, memory-based m…

Continual LearningOut-of-Distribution Generalization