paper-with-me

Papers

How Relevant is Selective Memory Population in Lifelong Language Learning?

2022-10-03 · Vladimir Araujo, Helena Balabin, Julio Hurtado, Alvaro Soto, Marie-Francine Moens

Lifelong language learning seeks to have models continuously learn multiple tasks in a sequential order without suffering from catastrophic forgetting. State-of-the-art approaches rely on sparse experience replay as the primary approach to prevent forgetting. Experience replay usually adopts sampling methods for the memory population; however, the effect of the chosen sampling strategy on model performance has not yet been studied. In this paper, we investigate how relevant the selective memory population is in the lifelong learning process of text classification and question-answering tasks. We found that methods that randomly store a uniform number of samples from the entire data stream lead to high performances, especially for low memory size, which is consistent with computer vision studies.

📄 PDF Abstract BibTeX arXiv:2210.00940

Code (0)

등록된 구현이 없습니다.

Tasks

Lifelong learningQuestion Answeringtext-classificationText Classification

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Similar Papers 제목 키워드 기반

Sharing Less is More: Lifelong Learning in Deep Networks with Selective Layer Transfer

2021-01-01 · ICML Workshop LifelongML 2020 7 · Seungwon Lee, Sima Behpour, Eric Eaton

Effective lifelong learning across diverse tasks requires diverse knowledge, yet transferring irrelevant knowledge may lead to interference and catastrophic forgetting. In deep networks, transferring the appropriate gran…

Lifelong learning

Uncovering Selective State Space Model's Capabilities in Lifelong Sequential Recommendation

2024-03-25 · Jiyuan Yang, Yuanzi Li, Jingyu Zhao, Hanbing Wang 외

Sequential Recommenders have been widely applied in various online services, aiming to model users' dynamic interests from their sequential interactions. With users increasingly engaging with online platforms, vast amoun…

2kMambaSequential Recommendation

LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners

2025-05-17 · Junhao Zheng, Xidi Cai, Qiuke Li, Duzhen Zhang 외

Lifelong learning is essential for intelligent agents operating in dynamic environments. Current large language model (LLM)-based agents, however, remain stateless and unable to accumulate or transfer knowledge over time…

Language ModelingLanguage ModellingLarge Language ModelLifelong learning

Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation

2022-07-01 · NAACL 2022 7 · Dingcheng Li, Zheng Chen, Eunah Cho, Jie Hao 외

Seq2seq language generation models that are trained offline with multiple domains in a sequential fashion often suffer from catastrophic forgetting. Lifelong learning has been proposed to handle this problem. However, ex…

Domain AdaptationLifelong learningResponse GenerationText Generation

LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

2023-12-07 · Ying Wang, Yanlai Yang, Mengye Ren

In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval. LifelongMemory generates concise video activity…

EgoSchemaFormQuestion AnsweringRetrieval