mlsanityData to 13 Oct 2026

Multi-Source Domain Adaptation with Mixture of Experts

arXiv 1809.02256 ↗First posted 7 Sep 2018cs.CLcited by 62

On the map: Mixture-of-experts → MoE large language models

Abstract (arXiv)

We propose a mixture-of-experts approach for unsupervised domain adaptation from multiple sources. The key idea is to explicitly capture the relationship between a target example and different source domains. This relationship, expressed by a point-to-set metric, determines how to combine predictors trained on various domains. The metric is learned in an unsupervised fashion using meta-training. Experimental results on sentiment analysis and part-of-speech tagging demonstrate that our approach consistently outperforms multiple baselines and can robustly handle negative transfer.

Key facts. Cited by 62 papers in the map (data through 13 Oct 2026). Placed in MoE large language models, one of 12 directions in Mixture-of-experts. Builds on 14 of its 39 references that are in the map. First posted on arXiv 7 Sep 2018.

Builds on

14 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer23 Jan

Other references · 13

  1. 2015Domain-Adversarial Training of Neural Networkscited by 3,030
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,011
  3. 2016Matching Networks for One Shot Learningcited by 2,251
  4. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,126
  5. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 597
  6. 2016Domain Separation Networkscited by 318
  7. 2017Learning to select data for transfer learning with Bayesian Optimizationcited by 64
  8. 2018Diverse Few-Shot Text Classification with Multiple Metricscited by 61
  9. 2018Multinomial Adversarial Networks for Multi-Domain Text Classificationcited by 40
  10. 2016Neural Structural Correspondence Learning for Domain Adaptationcited by 19
  11. 2018Parsing Tweets into Universal Dependenciescited by 19
  12. 2017Knowledge Adaptation: Teaching to Adaptcited by 17
1 more
  1. 2017Aspect-augmented Adversarial Networks for Domain Adaptationcited by 12

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 20; 2022: 8; 2023: 9; 2024: 13; 2025: 6; 2026: 4.

62 papers.

Sort:

By area:

  1. 2024BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domainscited by 299
  2. 2021DEMix Layers: Disentangling Domains for Modular Language Modelingcited by 130
  3. 2025A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applicationscited by 91
  4. 2022Sparse Mixture-of-Experts are Domain Generalizable Learnerscited by 85
  5. 2023Modular Deep Learningcited by 83
  6. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
  7. 2021Unsupervised Multi-source Domain Adaptation Without Access to Source Datacited by 76
  8. 2021A Survey on Stance Detection for Mis- and Disinformation Identificationcited by 75
  9. 2021PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domainscited by 61
  10. 2021Your Classifier can Secretly Suffice Multi-Source Domain Adaptationcited by 42
  11. 2021UDALM: Unsupervised Domain Adaptation through Language Modelingcited by 33
  12. 2021AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decodingcited by 32
38 more
  1. 2021Cross-Domain Label-Adaptive Stance Detectioncited by 30
  2. 2022Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofingcited by 28
  3. 2024MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detectioncited by 27
  4. 2021T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptationcited by 24
  5. 2021CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learningcited by 23
  6. 2021FastSurferVINN: Building Resolution-Independence into Deep Learning Segmentation Methods -- A Solution for HighRes Brain MRIcited by 19
  7. 2022On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptationcited by 16
  8. 2022Example-based Hypernetworks for Out-of-Distribution Generalizationcited by 16
  9. 2023A Data Fusion Framework for Multi-Domain Morality Learningcited by 14
  10. 2021Secure Domain Adaptation with Multiple Sourcescited by 12
  11. 2021Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularizationcited by 12
  12. 2021NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Trainingcited by 11
  13. 2021Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLPcited by 10
  14. 2022DAME: Domain Adaptation for Matching Entitiescited by 9
  15. 2024More is Better: Deep Domain Adaptation with Multiple Sourcescited by 9
  16. 2022HMOE: Hypernetwork-based Mixture of Experts for Domain Generalizationcited by 8
  17. 2024LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalizationcited by 8
  18. 2021Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classificationcited by 7
  19. 2023Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answeringcited by 6
  20. 2024Domain adaptation in small-scale and heterogeneous biological datasetscited by 5
  21. 2019A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Expertscited by 4
  22. 2024What the Weight?! A Unified Framework for Zero-Shot Knowledge Compositioncited by 4
  23. 2024Estimating Causal Effects of Text Interventions Leveraging LLMscited by 4
  24. 2025Aggregate to Adapt: Node-Centric Aggregation for Multi-Source-Free Graph Domain Adaptationcited by 4
  25. 2021Learning to Share by Masking the Non-shared for Multi-domain Sentiment Classificationcited by 3
  26. 2022Multiple-Source Domain Adaptation via Coordinated Domain Encoders and Paired Classifierscited by 3
  27. 2024Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysiscited by 3
  28. 2025Sci-LoRA: Mixture of Scientific LoRAs for Cross-Domain Lay Paraphrasingcited by 3
  29. 2025Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentationcited by 3
  30. 2025RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domainscited by 3
  31. 2021Ensemble Learning-Based Approach for Improving Generalization Capability of Machine Reading Comprehension Systemscited by 2
  32. 2023Approximately optimal domain adaptation with Fisher's Linear Discriminantcited by 2
  33. 2023Domain Adaptation for Inertial Measurement Unit-based Human Activity Recognition: A Surveycited by 2
  34. 2023Measuring Your ASTE Models in The Wild: A Diversified Multi-domain Dataset For Aspect Sentiment Triplet Extractioncited by 2
  35. 2023Differentiable Weight Masks for Domain Transfercited by 2
  36. 2023Multi-source domain adaptation for regressioncited by 2
  37. 2021AIREX: Neural Network-based Approach for Air Quality Inference in Unmonitored Citiescited by 1
  38. 2022Domain Generalization via Selective Consistency Regularization for Time Series Classificationcited by 1

50 most cited of 62 All 62 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Flexible and Effective Mixing of Large Language Models into a Mixture of Domain Experts
  2. 2025A Tale of Two Experts: Cooperative Learning for Source-Free Unsupervised Domain Adaptation
  3. 2020Transformer Based Multi-Source Domain Adaptation
  4. 2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts
  5. 2024Scalable Multi-Domain Adaptation of Language Models using Modular Experts
  6. 2024Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation
  7. 2023Adapt in Contexts: Retrieval-Augmented Domain Adaptation via In-Context Learning
  8. 2026Harnessing Domain Specialists in Multimodal Mixture-of-Experts for Efficient Adaptation