paper-with-me

Papers

GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning

2021-11-18 · CVPR 2022 1 · Rishabh Tiwari, KrishnaTeja Killamsetty, Rishabh Iyer, Pradeep Shenoy

Continual learning (CL) aims to develop techniques by which a single model adapts to an increasing number of tasks encountered sequentially, thereby potentially leveraging learnings across tasks in a resource-efficient manner. A major challenge for CL systems is catastrophic forgetting, where earlier tasks are forgotten while learning a new task. To address this, replay-based CL approaches maintain and repeatedly retrain on a small buffer of data selected across encountered tasks. We propose Gradient Coreset Replay (GCR), a novel strategy for replay buffer selection and update using a carefully designed optimization criterion. Specifically, we select and maintain a "coreset" that closely approximates the gradient of all the data seen so far with respect to current model parameters, and discuss key strategies needed for its effective application to the continual learning setting. We show significant gains (2%-4% absolute) over the state-of-the-art in the well-studied offline continual learning setting. Our findings also effectively transfer to online / streaming CL settings, showing upto 5% gains over existing approaches. Finally, we demonstrate the value of supervised contrastive loss for continual learning, which yields a cumulative gain of up to 5% accuracy when combined with our subset selection strategy.

📄 PDF Abstract BibTeX arXiv:2111.11210

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

Supervised Contrastive Loss 설명 없음

Similar Papers 제목 키워드 기반

PDAC: Efficient Coreset Selection for Continual Learning via Probability Density Awareness

2025-11-12 · Junqi Gao, Zhichang Guo, Dazhi Zhang, Yao Li 외 arxiv

Rehearsal-based Continual Learning (CL) maintains a limited memory buffer to store replay samples for knowledge retention, making these approaches heavily reliant on the quality of the stored samples. Current Rehearsal-b…

Continual Learning

Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm

2023-09-21 · NeurIPS 2023 11

Coreset is a small set that provides a data summary for a large dataset, such that training solely on the small set achieves competitive performance compared with a large dataset. In rehearsal-based continual learning, t…

Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers

2026-04-09 · Danit Yanowsky, Daphna Weinshall arxiv

Catastrophic forgetting remains a key challenge in Continual Learning (CL). In replay-based CL with severe memory constraints, performance critically depends on the sample selection strategy for the replay buffer. Most e…

Continual Learning

Gradient based sample selection for online continual learning

2019-03-20 · NeurIPS 2019 12 · Rahaf Aljundi, Min Lin, Baptiste Goujaud, Yoshua Bengio

A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known p…

class-incremental learningClass Incremental LearningContinual LearningDiversity

Online Coreset Selection for Rehearsal-based Continual Learning

2021-06-02 · ICLR 2022 4 · Jaehong Yoon, Divyam Madaan, Eunho Yang, Sung Ju Hwang

A dataset is a shred of crucial evidence to describe a task. However, each data point in the dataset does not have the same potential, as some of the data points can be more representative or informative than others. Thi…

Continual Learning