paper-with-me

Papers

Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning

2026-01-24 · Fatema Siddika, Md Anwar Hossen, Tanwi Mallick, Ali Jannesari arxiv

Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge. Existing methods typically treat parameters uniformly, failing to distinguish between specific task knowledge and shared capabilities. We introduce Mixture of Sparse Experts for Task-Agnostic Continual Learning, referred to as SETA, a framework that resolves the plasticity-stability conflict by decomposing the model into modular subspaces. Unlike standard updates, where tasks compete for the same parameters, SETA separates knowledge into unique experts, designed to isolate task-specific patterns, and shared experts, responsible for capturing common features. This structure is maintained through elastic weight anchoring, which protects critical shared knowledge and enables a unified gating network to automatically retrieve the correct expert combination for each task during inference. Extensive experiments across diverse domain-specific and general benchmarks demonstrate that SETA consistently outperforms state-of-the-art parameter-efficient fine-tuning-based continual learning methods.

📄 PDF Abstract BibTeX arXiv:2601.17616

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuningContinual Learning

Similar Papers 제목 키워드 기반

Multi-Task Learning via Task Multi-Clustering

2019-05-16 · ICML Workshop AMTL 2019 6 · Anonymous

Multi-task learning has the potential to facilitate learning of shared representations between tasks, leading to better task performance. Some sets of tasks are related, and can share many features that are useful latent…

ClusteringMixture-of-ExpertsMulti-Task Learning

Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Traditional multi-task learning (MTL) methods use dense networks that use the same set of shared weights across several different tasks. This often creates interference where two or more tasks compete to pull model param…

Mixture-of-ExpertsMulti-Task Learning

Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners

2022-04-16 · Shashank Gupta, Subhabrata Mukherjee, Krishan Subudhi, Eduardo Gonzalez 외

Traditional multi-task learning (MTL) methods use dense networks that use the same set of shared weights across several different tasks. This often creates interference where two or more tasks compete to pull model param…

Mixture-of-ExpertsMulti-Task Learning

MoTE: Mixture of Task Experts for Multi-Task Video Understanding

2026-08-25 · Muhammad Asad Ali, Umar Khan, Nadia Robertini, Didier Stricker hf

Procedural video-language models must solve heterogeneous tasks from the same visual evidence, including action recognition, forecasting, and procedure prediction. Dense transformer decoders share the same feed-forward n…

Action Recognition

Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning

2025-10-01 · Minghao Yang, Ren Togo, Guang Li, Takahiro Ogawa 외 arxiv

Mixture-of-Experts (MoE) has emerged as a powerful framework for multi-task learning (MTL). However, existing MoE-MTL methods often rely on single-task pretrained backbones and suffer from redundant adaptation and ineffi…

Multi-Task Learning