Negative Transfer

Ask about this topic

Overview

Negative transfer studies when sharing learned features, parameters, data, or skills makes a target task perform worse than learning it independently. Researchers address it by screening or reweighting sources, clustering related tasks, and routing updates through specialized experts or lightweight adapters; these approaches appear in multi-task learning, federated learning, domain adaptation, and continual learning. Evaluation compares transfer with target-only baselines and increasingly tracks asymmetry, held-out performance, and person- or task-level losses rather than averages alone. The central challenge is deciding when knowledge will help: related tasks can still interfere, and isolation that prevents harm can also discard useful sharing.

Latest papers

CardsList

31 papers3 papers in the last four weeks, down 25% on the four weeks before. 0.0% of all new papers.

  1. STRATA: Self-Maintaining Structured Experience Graphs for Self-Evolving Language Agents

    Oct 14, 2026Guanhua Zhu, Hanwen Li, Zhi Wei +2LLM Agent Self-ImprovementAgent Memory Management

    Department of Informatics, New Jersey Institute of Technology · Department of Computer Science, New Jersey Institute of Technology · School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen

  2. Task-Oriented Rank Adaptation for Continual Learning in Text Classification

    Oct 1, 2026Rey Sanchez Lopez, Eduardo Morales Manzanares, Hugo Jair EscalanteContinual LearningLow-Rank Adaptation

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

  3. A helps B while B hurts A: directed transfer in instruction-tuning mixture

    Sep 30, 2026Nima H. Siboni, Vahid RostamiLLM Fine-TuningInstruction-Tuning Data Selection

    Juna.ai, Kastanienallee 32, 10435 Berlin, Germany · Computational Systems Neuroscience, Institute of Zoology, University of Cologne, Germany

  4. 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 NetworksFederated Graph Learning

    PES University, Bengaluru, India

  5. Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells

    Sep 10, 2026Narcis MarincatMulti-Agent CommunicationNegative Transfer

    Independent researcher.

  6. 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-TuningLow-Rank Adaptation

    1Islamic University of Technology · 2York University · 3Dialpad Inc.

  7. Similarity-Aware Personalized Federated Learning in Heterogeneous Environments

    Sep 2, 2026Arun Kumar A, Sunil Gupta, Dang Ngyuen +2Federated LearningNon-IID Federated Learning

    Applied Artificial Intelligence Initiative (A2I2) Deakin University, Australia

  8. Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents

    Aug 20, 2026Yiyang Feng, Biddut Sarker Bijoy, Niranjan Balasubramanian +1LLM Agent Skill LearningLLM Agent Skill Evaluation

    Computer Science Department, Stony Brook University, Stony Brook, USA

  9. When Adaptation Hurts: Split Sensitivity and Person-Level Negative Transfer in Federated Wearable Onboarding

    Aug 18, 2026Rahil Aftab, Vineet Kumar Rakesh, Soumya Mazumdar +1Federated LearningFederated Fine-Tuning

    Department of Computer Science and Engineering Jamia Hamdard New Delhi 110062, India · Engineering Science Homi Bhabha National Institute Anushaktinagar, Mumbai 400094, Maharashtra, India Computer and Informatics Group Variable Energy Cyclotron Centre 1/AF, Bidhannagar, Kolkata 700064, West Bengal, India · Department of Computer Science and Business Systems Gargi Memorial Institute of Technology Affiliated to Maulana Abul Kalam Azad University of Technology Balarampur, Mouza Beralia, Baruipur, Kolkata 700144, West Bengal, India

  10. VERDI:Verified Contradictions for Continual World-Model Optimization

    Aug 10, 2026Junyu Wu, Shiqin Nie, Youyi Kou +10World Model LearningWorld Models

    * Equal contribution

  11. Semantic-Aware Task Clustering for Constructive and Cooperative Multi-Tasking

    Jul 23, 2026Ahmad Halimi Razlighi, Maximilian H. V. Tillmann, Edgar Beck +2ClusteringSemantic Communication

    Department of Communications Engineering, University of Bremen, Germany · Communication Systems Group, Paderborn University, 33098 Paderborn, Germany

  12. Capacity and Redundancy Trade-offs in Multi-Task Learning

    Jul 17, 2026Asif KhanMulti-Task LearningMulti-Task Optimization

    1Harvard Medical School, Boston, USA

  13. Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach

    Jul 6, 2026Qian Hu, Bin Fan, Yao Xiao +2Transfer LearningPhysics-Informed ML

    School of Computing and Data Science, Fujian University of Technology, Fuzhou, 350118, Fujian, China

  14. Transfer Learning in High-dimensional Ising Models

    Jul 3, 2026Joonho Kim, Seyoung ParkGraph Structure LearningIsing 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

  15. Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems

    Jun 15, 2026Roberto GarroneCross-Domain Transfer LearningTransfer Learning

    Open University of Cyprus

  16. When Good Verifiers Go Bad: Silent Negative Transfer in Verifier-Guided VLM Training

    Jun 12, 2026Jianzhe LinVLM EvaluationVLM Adaptation

    MetaAI · Work done at Meta

  17. Hierarchical Projection for Adaptive Knowledge Transfer

    Jun 7, 2026Samhita Pal, Tian GuHierarchical Bayesian ModelingCross-Domain Transfer Learning

    Vanderbilt University Medical Center · Columbia University

  18. The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathematical Reasoning

    Jun 5, 2026Rahul Nair, Chun TaoFine-TuningSmall Language Models

  19. Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring

    May 28, 2026Youhan Huang, Jiajun Li, Yilin Fang +2Vision TransformerMulti-Task Learning

    1Beijing University of Posts and Telecommunications, Beijing, China · 2Beijing University of Chemical Technology, Beijing, China · 3Capital Medical University, Beijing, China

  20. From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills

    May 22, 2026Zisu Huang, Jingwen Xu, Yifan Yang +13LLM Agent EvaluationLLM Agent Skill Learning

    Fudan University · Microsoft Research · Shanghai Jiao Tong University

  21. DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation

    May 15, 2026Yifan Gao, Lu Zou, Zhangjin Huang +1Object Pose EstimationGradient 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

  22. Eradicating Negative Transfer in Multi-Physics Foundation Models via Sparse Mixture-of-Experts Routing

    May 14, 2026Ellwil Sharma, Arastu SharmaSparse Mixture-of-ExpertsPDE Operator Learning

    Shodh AI

  23. Language-Induced Priors for Domain Adaptation

    May 14, 2026Qiyuan Chen, Jiayu Zhou, Raed Al KontarMulti-Source Domain AdaptationDomain Adaptation

    Industrial and Operations Engineering University of Michigan Ann Arbor, MI 48109 · School of Information University of Michigan Ann Arbor, MI 48109

  24. B3\mathcal{B}^{3}-Net: Controlled Posterior Bridge Learning for Multi-Task Dense Prediction

    May 7, 2026Meihua Zhou, Li YangMulti-Task LearningDense Prediction

    Wannan Medical University, Wuhu, China · University of Chinese Academy of Sciences, Beijing, China

  25. FedeKD: Energy-Based Gating for Robust Federated Knowledge Distillation under Heterogeneous Settings

    May 7, 2026Quang-Huy Nguyen, Jiaqi Wang, Wei-shinn KuFederated Knowledge DistillationKnowledge Distillation

    Department of Computer Science and Software Engineering Auburn University Auburn, AL 36849

  26. Channel Adaptation for EEG Foundation Models: A Systematic Benchmark Across Architectures, Tasks, and Training Regimes

    Apr 25, 2026Kuntal Kokate, Bruno Aristimunha, Dung Truong +1Fine-TuningEEG 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

  27. Transfer learning for nonparametric Bayesian networks

    Apr 1, 2026Rafael Sojo, Pedro Larrañaga, Concha BielzaBayesian Network Structure LearningTransfer Learning

    Aingura IIoT, Paseo Mikeletegui 43, 20009 Donostia-San Sebastián, Gipuzkoa, Spain · Universidad Politécnica de Madrid, Departamento de Inteligencia Artificial, 28660 Boadilla del Monte, Madrid, Spain

  28. CORAL: Scalable Multi-Task Robot Learning via LoRA Experts

    Mar 10, 2026Yuankai Luo, Woping Chen, Tong Liang +1Robot LearningContinual Robot Learning

    Frontier Robotics

  29. Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection

    Mar 8, 2026Rui Ding, Meng Yang, Nanning ZhengMonocular 3D Object DetectionCross-Modal Knowledge Distillation

    Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, P.R.China.

  30. Multi-Task Learning for Metal Alloy Property Prediction: An Empirical Study of Negative Transfer and Mitigation Strategies

    Dec 28, 2025Sungwoo KangMulti-Task LearningMaterials Property Prediction

    Department of Electrical and Computer Engineering, Korea University, Seoul 02841, Republic of Korea