Negative Transfer

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 24

All topics

Task-Oriented Rank Adaptation for Continual Learning in Text Classification
Oct 1, 2026Rey Sanchez Lopez, Eduardo Morales Manzanares, Hugo Jair EscalanteContinual Learning Low-Rank Adaptation
INAOE, Puebla, Mexico · The University of Texas at El Paso, El Paso, TX, USA
A helps B while B hurts A: directed transfer in instruction-tuning mixture
Sep 30, 2026Nima H. Siboni, Vahid RostamiLLM Fine-Tuning Instruction-Tuning Data Selection
Juna.ai, Kastanienallee 32, 10435 Berlin, Germany · Computational Systems Neuroscience, Institute of Zoology, University of Cologne, Germany
Structural Negative Transfer in Federated Graph Neural Networks: Diagnosis, Causal Investigation, and the Limits of Divergence-Aware Mitigation
Sep 15, 2026Chethana Prasad Kabgere, Shylaja SSGraph Neural Networks Federated Graph Learning
PES University, Bengaluru, India
Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells
Sep 12, 2026Narcis MarincatMulti-Agent Communication Negative Transfer
Independent researcher.
Routing Is Not Enough: Diagnosing Intra-Adapter Subspace Contention in MoE+LoRA Fine-Tuning
Sep 2, 2026Mehreen Hossain Chowdhury, Nowshin Mahjabin, Ahmed Shafin Ruhan +3Fine-Tuning Low-Rank Adaptation
1Islamic University of Technology · 2York University · 3Dialpad Inc.
Similarity-Aware Personalized Federated Learning in Heterogeneous Environments
Sep 2, 2026Arun Kumar A, Sunil Gupta, Dang Ngyuen +2Federated Learning Non-IID Federated Learning
Applied Artificial Intelligence Initiative (A2I2) Deakin University, Australia
verdi: retrieval is not transfer for continual world model optimization
Aug 10, 2026Junyu Wu, Shiqin Nie, Youyi Kou +9World Model Learning World Models
* Equal contribution · ‡ Project leader, † Corresponding author · † Corresponding author
Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking
Jul 23, 2026Ahmad Halimi Razlighi, Maximilian H. V. Tillmann, Edgar Beck +2Clustering Semantic Communication
Department of Communications Engineering, University of Bremen, Germany · Communication Systems Group, Paderborn University, 33098 Paderborn, Germany
Capacity and Redundancy Trade-offs in Multi-Task Learning
Jul 17, 2026Asif KhanMulti-Task Learning Multi-Task Optimization
1Harvard Medical School, Boston, USA
Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach
Jul 6, 2026Qian Hu, Bin Fan, Yao Xiao +2Transfer Learning Physics-Informed ML
School of Computing and Data Science, Fujian University of Technology, Fuzhou, 350118, Fujian, China
Transfer Learning in High-dimensional Ising Models
Jul 3, 2026Joonho Kim, Seyoung ParkGraph Structure Learning Ising Model
Kim Jaechul Graduate School of Artificial Intelligence, KAIST, Seoul, Republic of Korea · Department of Statistics and Data Science, Yonsei University, Seoul, Republic of Korea
Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems
Jun 15, 2026Roberto GarroneCross-Domain Transfer Learning Transfer Learning
Open University of Cyprus
When Good Verifiers Go Bad: Silent Negative Transfer in Verifier-Guided VLM Training
Jun 12, 2026Jianzhe LinVLM Evaluation VLM Adaptation
MetaAI · Work done at Meta
Hierarchical Projection for Adaptive Knowledge Transfer
Jun 7, 2026Samhita Pal, Tian GuHierarchical Bayesian Modeling Cross-Domain Transfer Learning
Vanderbilt University Medical Center · Columbia University
The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning
Jun 5, 2026Rahul Nair, Chun TaoFine-Tuning Small Language Models
Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring
May 28, 2026Youhan Huang, Jiajun Li, Yilin Fang +2Vision Transformer Multi-Task Learning
1Beijing University of Posts and Telecommunications, Beijing, China · 2Beijing University of Chemical Technology, Beijing, China · 3Capital Medical University, Beijing, China
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
May 22, 2026Zisu Huang, Jingwen Xu, Yifan Yang +13LLM Agent Evaluation LLM Agent Skill Learning
Fudan University · Microsoft Research · Shanghai Jiao Tong University
DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation
May 15, 2026Yifan Gao, Lu Zou, Zhangjin Huang +1Object Pose Estimation Gradient Interference
Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, Hubei, China · University of Science and Technology of China, Hefei, Anhui, China · Peking University, Beijing, China
Eradicating Negative Transfer in Multi-Physics Foundation Models via Sparse Mixture-of-Experts Routing
May 14, 2026Ellwil Sharma, Arastu SharmaSparse Mixture-of-Experts PDE Operator Learning
Shodh AI
Language-Induced Priors for Domain Adaptation
May 14, 2026Qiyuan Chen, Jiayu Zhou, Raed Al KontarMulti-Source Domain Adaptation Domain Adaptation
Industrial and Operations Engineering University of Michigan Ann Arbor, MI 48109 · School of Information University of Michigan Ann Arbor, MI 48109
$\mathcal{B}^{3}$ -Net: Controlled Posterior Bridge Learning for Multi-Task Dense Prediction
May 7, 2026Meihua Zhou, Li YangMulti-Task Learning Dense Prediction
Wannan Medical University, Wuhu, China · University of Chinese Academy of Sciences, Beijing, China
FedeKD: Energy-Based Gating for Robust Federated Knowledge Distillation under Heterogeneous Settings
May 7, 2026Quang-Huy Nguyen, Jiaqi Wang, Wei-shinn KuFederated Knowledge Distillation Knowledge Distillation
Department of Computer Science and Software Engineering Auburn University Auburn, AL 36849
Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes
Apr 25, 2026Kuntal Kokate, Bruno Aristimunha, Dung Truong +1Fine-Tuning EEG Decoding
Swartz Center for Computational Neuroscience, Institute for Neural Computation, University of California San Diego, La Jolla, CA 92093, USA · Yneuro, Paris, France · Centre de Recherche Cerveau et Cognition, CNRS, Université Paul Sabatier, Toulouse, France
HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies
Dec 5, 2025Zhiying Du, Bei Liu, Yaobo Liang +7Visuomotor Policy Learning Vision-Language-Action Models
1Fudan University · 2Microsoft Research Asia · 3Xi’an Jiaotong University +1

Oct 1, 2026, cs.CLJ/K move · Enter open · S save

Task-Oriented Rank Adaptation for Continual Learning in Text Classification

Rey Sanchez Lopez, Eduardo Morales Manzanares, Hugo Jair Escalante

INAOE, Puebla, Mexico · The University of Texas at El Paso, El Paso, TX, USA

Continual Learning Low-Rank Adaptation Negative Transfer Parameter-Efficient Fine-Tuning Catastrophic Forgetting

Open paper AskPDF arXiv

Continual learning (CL) in text classification faces two critical challenges: catastrophic forgetting and negative transfer across sequential tasks. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA enable efficient adaptation by learning low-rank updates of the model parameters. However, these compact representations are normally trained in isolation, limiting their reuse across related tasks. We introduce Task-Oriented Rank Adaptation (TORA), a geometric routing framework that leverages the low-rank structure of LoRA adapters to decide whether to transfer knowledge from the most compatible expert (Boosting) or isolate the new task (Shielding) based on structural similarity. Evaluated across 15 diverse text classification benchmarks, TORA consistently avoids harmful routing decisions: compatible tasks exceed their isolated performance while reducing training time, and structurally distant tasks are protected from interference with no loss in accuracy. With a single geometric threshold and no reliance on task identities or predefined sequences, TORA provides a simple and effective approach for dynamic adapter routing in sequential text classification systems.

Momentum

Related topics

Latest papers 24