mlsanityData to 7 Oct 2026

A Survey on Negative Transfer

arXiv 2009.00909 ↗First posted 2 Sep 2020cs.LG cs.CV stat.MLcited by 120

Not on the map. Why?

Abstract (arXiv)

Transfer learning (TL) utilizes data or knowledge from one or more source domains to facilitate the learning in a target domain. It is particularly useful when the target domain has very few or no labeled data, due to annotation expense, privacy concerns, etc. Unfortunately, the effectiveness of TL is not always guaranteed. Negative transfer (NT), i.e., leveraging source domain data/knowledge undesirably reduces the learning performance in the target domain, has been a long-standing and challenging problem in TL. Various approaches have been proposed in the literature to handle it. However, there does not exist a systematic survey on the formulation of NT, the factors leading to NT, and the algorithms that mitigate NT. This paper fills this gap, by first introducing the definition of NT and its factors, then reviewing about fifty representative approaches for overcoming NT, according to four categories: secure transfer, domain similarity estimation, distant transfer, and NT mitigation. NT in related fields, e.g., multi-task learning, lifelong learning, and adversarial attacks, are also discussed.

Key facts. Cited by 120 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 11; 2023: 23; 2024: 24; 2025: 37; 2026: 24.

120 papers.

Sort:

By area:

  1. 2024Representation Surgery for Multi-Task Model Mergingcited by 95
  2. 2022ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Promptscited by 85
  3. 2023Exploring the Benefits of Training Expert Language Models over Instruction Tuningcited by 80
  4. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  5. 2023SGL-PT: A Strong Graph Learner with Graph Prompt Tuningcited by 35
  6. 2023Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphscited by 29
  7. 2022Improving Multi-Task Generalization via Regularizing Spurious Correlationcited by 28
  8. 2023ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learningcited by 28
  9. 2023Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalizationcited by 28
  10. 2023Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectivescited by 24
  11. 2025CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Mergingcited by 22
  12. 2025How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?cited by 19
38 more
  1. 2024Subgraph Pooling: Tackling Negative Transfer on Graphscited by 17
  2. 2022An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systemscited by 16
  3. 2022Transferability-Guided Cross-Domain Cross-Task Transfer Learningcited by 13
  4. 2023Tangent Transformers for Composition, Privacy and Removalcited by 13
  5. 2022muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systemscited by 12
  6. 2024SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgerycited by 12
  7. 2025Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflictscited by 11
  8. 2024Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understandingcited by 10
  9. 2022A Continual Development Methodology for Large-scale Multitask Dynamic ML Systemscited by 9
  10. 2023MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasetscited by 9
  11. 2024More is Better: Deep Domain Adaptation with Multiple Sourcescited by 9
  12. 2024Federated Graph Learning for Cross-Domain Recommendationcited by 9
  13. 2023Pay Less But Get More: A Dual-Attention-based Channel Estimation Network for Massive MIMO Systems with Low-Density Pilotscited by 8
  14. 2023IDA: Informed Domain Adaptive Semantic Segmentationcited by 8
  15. 2024Dynamic Transformer Architecture for Continual Learning of Multimodal Taskscited by 8
  16. 2026CORAL: Scalable Multi-Task Robot Learning via LoRA Expertscited by 8
  17. 2023Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Rankingcited by 7
  18. 2024DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Seriescited by 7
  19. 2025Revisiting Euclidean Alignment for Transfer Learning in EEG-Based Brain-Computer Interfacescited by 7
  20. 2021Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta reviewcited by 6
  21. 2022Knowledge Sharing via Domain Adaptation in Customs Fraud Detectioncited by 5
  22. 2024Knowledge Transfer from Simple to Complex: A Safe and Efficient Reinforcement Learning Framework for Autonomous Driving Decision-Makingcited by 5
  23. 2025Task Vector Quantization for Memory-Efficient Model Mergingcited by 5
  24. 2023Benchmarking Domain Adaptation for Chemical Processes on the Tennessee Eastman Processcited by 4
  25. 2024Free Form Medical Visual Question Answering in Radiologycited by 4
  26. 2025Learning Policy Committees for Effective Personalization in MDPs with Diverse Taskscited by 4
  27. 2025A Large-scale Benchmark on Geological Fault Delineation Models: Domain Shift, Training Dynamics, Generalizability, Evaluation and Inferential Behaviorcited by 4
  28. 2025On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentationcited by 4
  29. 2025MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptationcited by 4
  30. 2022Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classificationcited by 3
  31. 2023Bayesian Transfer Learningcited by 3
  32. 2024Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learningcited by 3
  33. 2024Help Me Help You: The Aggregate Value of Source and Target Data in Transfer Learningcited by 3
  34. 2024Federated Communication-Efficient Multi-Objective Optimizationcited by 3
  35. 2024Cross-Task Inconsistency Based Active Learning (CTIAL) for Emotion Recognitioncited by 3
  36. 2025Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environmentscited by 3
  37. 2022A Multiagent Framework for the Asynchronous and Collaborative Extension of Multitask ML Systemscited by 2
  38. 2023Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learningcited by 2

50 most cited of 120 All 120 (JSON)