# A Survey on Negative Transfer

arXiv: https://arxiv.org/abs/2009.00909 · HTML: https://mlsanity.com/paper/2009.00909/

## Key facts

- Cited by 122 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Sep 2020.

## Built on by (most cited first, 30 of 122)

- [Representation Surgery for Multi-Task Model Merging](https://mlsanity.com/paper/2402.02705/) (2024)
- [ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts](https://mlsanity.com/paper/2205.11961/) (2022)
- [Exploring the Benefits of Training Expert Language Models over Instruction Tuning](https://mlsanity.com/paper/2302.03202/) (2023)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [SGL-PT: A Strong Graph Learner with Graph Prompt Tuning](https://mlsanity.com/paper/2302.12449/) (2023)
- [Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs](https://mlsanity.com/paper/2304.10668/) (2023)
- [Improving Multi-Task Generalization via Regularizing Spurious Correlation](https://mlsanity.com/paper/2205.09797/) (2022)
- [ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning](https://mlsanity.com/paper/2301.12618/) (2023)
- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging](https://mlsanity.com/paper/2505.06977/) (2025)
- [How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?](https://mlsanity.com/paper/2501.11253/) (2025)
- [Subgraph Pooling: Tackling Negative Transfer on Graphs](https://mlsanity.com/paper/2402.08907/) (2024)
- [An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems](https://mlsanity.com/paper/2205.12755/) (2022)
- [Transferability-Guided Cross-Domain Cross-Task Transfer Learning](https://mlsanity.com/paper/2207.05510/) (2022)
- [Tangent Transformers for Composition, Privacy and Removal](https://mlsanity.com/paper/2307.08122/) (2023)
- [Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts](https://mlsanity.com/paper/2501.15065/) (2025)
- [muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems](https://mlsanity.com/paper/2205.10937/) (2022)
- [SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery](https://mlsanity.com/paper/2410.14389/) (2024)
- [Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understanding](https://mlsanity.com/paper/2407.05910/) (2024)
- [A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems](https://mlsanity.com/paper/2209.07326/) (2022)
- [MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets](https://mlsanity.com/paper/2307.02100/) (2023)
- [More is Better: Deep Domain Adaptation with Multiple Sources](https://mlsanity.com/paper/2405.00749/) (2024)
- [Federated Graph Learning for Cross-Domain Recommendation](https://mlsanity.com/paper/2410.08249/) (2024)
- [CORAL: Scalable Multi-Task Robot Learning via LoRA Experts](https://mlsanity.com/paper/2603.09298/) (2026)
- [Pay Less But Get More: A Dual-Attention-based Channel Estimation Network for Massive MIMO Systems with Low-Density Pilots](https://mlsanity.com/paper/2303.00986/) (2023)
- [IDA: Informed Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2303.02741/) (2023)
- [Dynamic Transformer Architecture for Continual Learning of Multimodal Tasks](https://mlsanity.com/paper/2401.15275/) (2024)
- [Towards the Better Ranking Consistency: A Multi-task Learning Framework for Early Stage Ads Ranking](https://mlsanity.com/paper/2307.11096/) (2023)
- [DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series](https://mlsanity.com/paper/2404.11269/) (2024)

## 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.