paper-with-me

홈 › Papers

Learning a Low-Rank Feature Representation: Achieving Better Trade-Off between Stability and Plasticity in Continual Learning

2023-12-14 · Zhenrong Liu, Yang Li, Yi Gong, Yik-Chung Wu

In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach optimizes network parameters in the null space of the past tasks' feature representation matrix to guarantee the stability. Concurrently, we judiciously select only a subset of neurons in each layer of the network while training individual tasks to learn the past tasks' feature representation matrix in low-rank. This increases the null space dimension when designing network parameters for subsequent tasks, thereby enhancing the plasticity. Using CIFAR-100 and TinyImageNet as benchmark datasets for continual learning, the proposed approach consistently outperforms state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2312.08740

Code (1)

dacaidi/lrfr 공식 구현 pytorch

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach

2021-05-17 · Xu Ma, Pengjie Wang, Hui Zhao, Shaoguo Liu 외

In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. Such architecture usually consists of matching, pre-ranking, ranking, and re-ranking stages. In the…

feature selectionRe-Ranking

Parallel Gaussian Process Regression for Big Data: Low-Rank Representation Meets Markov Approximation

2014-11-17 · Kian Hsiang Low, Jiangbo Yu, Jie Chen, Patrick Jaillet

The expressive power of a Gaussian process (GP) model comes at a cost of poor scalability in the data size. To improve its scalability, this paper presents a low-rank-cum-Markov approximation (LMA) of the GP model that i…

regression

Scoring Is Not Enough: Addressing Gaps in Utility-fairness Trade-offs for Ranking

2026-06-24 · Shubham Singh, Ian A. Kash, Mesrob I. Ohannessian arxiv

Scoring functions are used to represent the relevance of individual documents. In modern information retrieval or recommendation systems, they are often learned from data and play a pivotal role in ranking sets of docume…

Recommendation SystemsInformation Retrieval

Fast Implicit Neural Light Field Representation via Geometric Decomposition and Multi-Resolution Low-Rank Features

2026-08-14 · Yao Guo, Ligen Shi, Shuchen Sun, Jun Qiu 외 arxiv

Implicit neural representations provide a compact and continuous way to reconstruct dense light fields from sampled ray coordinates. However, fast light field reconstruction remains challenging because a light field is a…

Joint Optimization of Cascade Ranking Models

2019-02-11 · WSDM 2019 2 · Luke Gallagher, Ruey-Chen Chen, Roi Blanco, J. Shane Culpepper

Reducing excessive costs in feature acquisition and model evaluation has been a long-standing challenge in learning-to-rank systems. A cascaded ranking architecture turns ranking into a pipeline of multiple stages, and h…

Ad-Hoc Information RetrievalDocument RankingInformation RetrievalLearning-To-Rank