The DOI matches its Crossref record; 38 of the 41 references it cites were found in a registry or an index.
Multi-Source Domain Adaptation with Mixture of Experts
Open accessAbstract
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 metatraining.Experimental results on sentiment analysis and part-of-speech tagging demonstrate that our approach consistently outperforms multiple baselines and can robustly handle negative transfer. 1
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In addition, we find that training on more diverse data with more product categories tends to improve generalization to unseen categories and reduce the effect of the distribution shift; similar phenomena have also been reported in prior work (Mansour et al., 2009; Guo et al., 2018).”
From WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020) · cites this paper as Guo et al., 2018
Citations
Cites
Convolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831
Domain-Adversarial Training of Neural Networks
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2017) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-3-319-58347-1_10 · Cited by 8,318
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636
Prototypical Networks for Few-shot LearningPreprint
Snell, J., Swersky, K., & Zemel, R. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.05175 · Cited by 6,245
Adaptive Mixtures of Local Experts
Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. (1991) · Neural Computation · doi:10.1162/neco.1991.3.1.79 · Cited by 5,384
Distance Metric Learning for Large Margin Nearest Neighbor Classification
Weinberger, K. Q., & Saul, L. K. (2009) · Journal of Machine Learning Research · doi:10.5555/1577069.1577078 · Cited by 4,652
(2012) · MPG.PuRe (Max Planck Society) · doi:10.5555/2188385.2188410 · Cited by 3,603
Deep domain confusion Maximizing for domain invariance
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., & Darrell, T. (2014) · arXiv · doi:10.48550/arxiv.1412.3474 · Cited by 2,285
Analysis of Representations for Domain Adaptation
Ben-David, S., Blitzer, J., Crammer, K., & Pereira, F. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0022 · Cited by 2,019
(2007) · Cited by 2,018
Cited by
Sorted by citations
Items 101–169 of 169
Loewinger, G. C., Patil, P., Kishida, K. T., & Parmigiani, G. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/856385 · Cited by 5
Den-ML: Multi-source cross-lingual transfer via denoising mutual learning
Ge, L., Hu, C., Ma, G., Zhang, H., & Liu, J. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2024.103834 · Cited by 4
Improving Cross-lingual Text Classification with Zero-shot Instance-Weighting
Li, I., Sen, P., Zhu, H., Li, Y., & Radev, D. (2021) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/2021.repl4nlp-1.1 · Cited by 4
Class-rebalanced wasserstein distance for multi-source domain adaptation
Wang, Q., Wang, S., & Wang, B. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03810-y · Cited by 4
Collaborative Learning of Diverse Experts for Source-free Universal Domain Adaptation
Shen, M., Lu, Y., Hu, Y., & Ma, A. J. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612211 · Cited by 4
Multi-domain Transfer Learning for Text Classification
Su, X., Li, R., & Li, X. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60450-9_36 · Cited by 4
Domain Adaptation for POS Tagging with Contrastive Monotonic Chunk-wise Attention
Mundotiya, R. K., Mehta, A., & Baruah, R. (2022) · Neural Processing Letters · doi:10.1007/s11063-022-10746-4 · Cited by 4
AIREX: Neural Network-based Approach for Air Quality Inference in Unmonitored Cities
Sasaki, Y., Harada, K., Yamasaki, S., & Onizuka, M. (2021) · International Conference on Mobile Data Management · doi:10.1109/mdm55031.2022.00037 · Cited by 4
Towards Distribution-shift Robust Text Classification of Emotional Content
Bulla, L., Aldo Gangemi, A., & Mongiovı̀, M. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.524 · Cited by 4
Effective transfer learning for low-resource natural language understanding
Liu, Z. (2022) · doi:10.14711/thesis-991013106358603412 · Cited by 6
How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing?
Jin, H., Dong, T., Hou, L., Li, J., Chen, H., Dai, Z., & Qu, Y. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.243 · Cited by 3
Transformer-Based Multi-Source Domain Adaptation Without Source Data
Li, G., & Wu, C. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191276 · Cited by 3
Lee, J., Frăsincar, F., & Truşcǎ, M. M. (2023) · ACM SIGAPP Applied Computing Review · doi:10.1145/3626307.3626309 · Cited by 3
Multi-Source Attention for Unsupervised Domain Adaptation
Cui, X., & Bollegala, D. (2020) · Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing (AACL-IJCNLP) · doi:10.18653/v1/2020.aacl-main.87 · Cited by 3
Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network
Li, Y., Li, S., & Zhang, M. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.74 · Cited by 3
Transductive Learning of Neural Language Models for Syntactic and Semantic Analysis
Ouchi, H., Suzuki, J., & Inui, K. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1379 · Cited by 3
AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive DecodingPreprint
Yan, J., Zalmout, N., Liang, Y., Grant, C., Ren, X., & Dong, X. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.02318 · Cited by 3
Mutual supervision multi-source-free domain adaptation of image classification
Tian, L., Zhou, L., Li, S., Gan, Y., & Ye, M. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113479 · Cited by 2
APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing
Li, Y., Zhang, M., Li, Z., Zhang, M., Wang, Z., Huai, B., & Yuan, N. J. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.149 · Cited by 2
Domain Generalization via Selective Consistency Regularization for Time Series Classification
Zhang, W., Ragab, M., & Foo, C.-S. (2022) · International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956338 · Cited by 2
Source distribution weighted multisource domain adaptation without access to source data
Ahmed, S. M., Raychaudhuri, D. S., Oymak, S., & Roy–Chowdhury, A. K. (2023) · Handbook of statistics · doi:10.1016/bs.host.2022.12.001 · Cited by 4
DA-Net: A Disentangled and Adaptive Network for Multi-Source Cross-Lingual Transfer Learning
Ge, L., Hu, C., Ma, G., Liu, J., & Zhang, H. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29761 · Cited by 2
Domain adaptation-based method for improving generalization of hate speech detection models
Nourollahi, S. F., Baradaran, R., & Amirkhani, H. (2024) · Archives de l'Institut d'Hessarek. · doi:10.61186/jsdp.21.1.125 · Cited by 2
The Impact of Ensemble Learning in Sentiment Analysis under Domain Shift
Özbey, C., Dilekoglu, B., & Aciksoz, S. (2021) · Innovations in Intelligent Systems and Applications Conference (ASYU) · doi:10.1109/asyu52992.2021.9599078 · Cited by 2
Anomaly Detection by Recombining Gated Unsupervised Experts
Schulze, J.-P., Sperl, P., & Böttinger, K. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892807 · Cited by 6
Cross-domain Slot Filling with Distinct Slot Entity and Type Prediction
Liu, S., Huang, P., Zhu, Z., Zhang, H., & Tan, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88480-2_41 · Cited by 2
Tawara, N., Ogawa, A., Iwata, T., Ashikawa, H., Kobayashi, T., & Ogawa, T. (2021) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2021edp7081 · Cited by 2
Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
Ye, H., Xie, Q., & Ng, H. T. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.537 · Cited by 6
Approximately Optimal Domain Adaptation with Fisher’s Linear Discriminant
Helm, H. S., Silva, A. D., Vogelstein, J. T., Priebe, C. E., & Yang, W. (2024) · Mathematics · doi:10.3390/math12050746 · Cited by 3
Soft Representation Learning for Sparse Transfer
Park, H., Yeo, J., Wang, G., & Hwang, S.-W. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1151 · Cited by 2
Risk Minimization for Zero-shot Sequence Labeling
Hu, Z., Jiang, Y., Bách, N., Wang, T., Huang, Z., Huang, F., & Tu, K. (2021) · doi:10.18653/v1/2021.acl-long.380 · Cited by 2
Multi-source domain adaptation for dependency parsing via domain-aware feature generation
Li, Y., Zhang, Z., Xian, Y., Yu, Z., Gao, S., Mao, C., & Huang, Y. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02306-0 · Cited by 1
Towards Recognizing Food Types for Unseen Subjects
Guan, J., Wang, J., Niu, W., Peng, Z., Wang, S., Liu, Z., Zhou, G., & Ren, B. (2024) · ACM Transactions on Computing for Healthcare · doi:10.1145/3696424 · Cited by 1
Lu, B., Shirai, K., & Kertkeidkachorn, N. (2025) · Information · doi:10.3390/info16050411 · Cited by 1
Scene generalization for biomedical fact verification via hierarchical mixture of experts
Si, J., Zhu, H., Zhao, Y., Zhang, W., Wang, T., Lü, W., & Zhou, D. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122527 · Cited by 1
MCDAN: Multi-Modal Cross-Domain Adaptation Network for Fake News Detection
Yang, H., Zhang, Q., & Zhang, Y. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401755 · Cited by 1
Cross-lingual Semantic Role Labelling with the ValPaL Database Knowledge
Choudhary, C., & O’Riordan, C. (2022) · Workshop on Knowledge Extraction and Integration for Deep Learning Architectures: Deep Learning Inside Out (DeeLIO) · doi:10.18653/v1/2022.deelio-1.1 · Cited by 1
Dynamic Network Model for Multi-Domain End-to-end Task-Oriented Dialogue System
Zhao, F., Qiu, M. L., Li, X., & Guo, D. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981938 · Cited by 1
Unsupervised Multi-Source Domains Adaptation with Locally Topological Persevering
Chen, Z.-F., Wang, L., Li, Y., & Ying, S.-H. (2023) · ACM Cloud and Autonomic Computing Conference · doi:10.1109/cac59555.2023.10451721
Low-resource entity resolution with domain generalization and active learning
Xu, Z., & Wang, N. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128131 · Cited by 1
Robust Multi-Prototypes Aware Integration for Zero-Shot Cross-Domain Slot Filling
Chen, S., Huang, P., Zhu, Z., Zhang, Y., & Xu, Y. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3495561 · Cited by 1
A Unified Adversarial Learning Framework for Semi-supervised Multi-target Domain Adaptation
Wu, X.-L., Wang, L., Wang, S., Meng, X.-F., Li, L.-F., Huang, H., Zhang, X., & Yan, J. (2020) · International Conference on Database Systems for Advanced Applications · doi:10.1007/978-3-030-59410-7_29
NLP Service APIs and Models for Efficient Registration of New Clients
Shah, S., Piratla, V., Chakrabarti, S., & Sarawagi, S. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.357 · Cited by 1
Towards data-free gating of heterogeneous pre-trained neural networks
Kang, C. W., Hong, C. M., & Maul, T. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02301-w · Cited by 1
Ensemble Model for Multi-Source Cross-Domain Sentiment Classification with Little Labeled Data
Lai, K.-P., Ho, J. C.-S., & Lam, W. P. (2020) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wiiat50758.2020.00038 · Cited by 1
Fine-grained Knowledge Fusion for Sequence Labeling Domain AdaptationPreprint
Yang, H., Huang, S., Dai, X., & Chen, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.04315
Metric Learning for Dynamic Text ClassificationPreprint
Wohlwend, J., Elenberg, E. R., Altschul, S., Henry, S., & Lei, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.01026
Learning Transferable Features for Unsupervised Domain Adaptation in Natural Language Processing
Cui, X. (2020) · University of Liverpool · doi:10.17638/03086091
Exploiting Domain-Aware Aspect Similarity for Multi-Source Cross-Domain Sentiment Classification
Lai, K.-P., Ho, J. C.-S., & Lam, W. P. (2021) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj060401
Enriching datasets for sentiment analysis in tweets with instance selection
Guimarães, E., Vianna, D., Paes, A., & Plastino, A. (2021) · Anais do Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) · doi:10.5753/kdmile.2021.17463
Neural semantic role labeling with more or less supervision
Cai, R. (2021) · ERA · doi:10.7488/era/1538
Exploring model transfer strategies for sentiment analysis in Twitter
Guimarães, E., Carvalho, J., Paes, A., & Plastino, A. (2021) · doi:10.5753/eniac.2021.18236
DIFL:Multi-Source Domain Adaptation for Point Clouds Using Domain-Invariant-Feature-LearningPreprint
Firkat, E., Huang, Y., Zhu, B., Mijit, T., Zhu, J., & Hamdulla, A. (2023) · doi:10.36227/techrxiv.23306399
Research on Multi-Domain Sample Classification Method Based on Baidu API
Cui, Y., Song, Q., Xue, Y., & Yu, J. (2023) · International Conference on Control, Robotics and Intelligent System (CCRIS) · doi:10.1145/3622896.3622899
Deconica: Deconfounding the Dataset Bias for Domain GeneralizationPreprint
Sheng, S., Shu, X., & Yan, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4616994
DeconICA: Deconfounding the Dataset Bias for Domain GeneralizationPreprint
Sheng, S., Shu, X., & Yan, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768682
Multi-Source Domain Adaptation for Emotion Classification Using Bi-LSTM and Broad Learning
Peng, S., & Cao, L. (2024) · Socio-affective computing · doi:10.1007/978-3-031-67718-2_6
Unsupervised and Adaptive Tor Website Fingerprinting
Zhang, G., Cao, J., Xu, M., & Deng, X. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-64954-7_11
Learning to Generalize Unseen Domains via Multi-source Meta Learning for Text Classification
Hu, Y., Zhang, C., Yang, M., Liang, X., Li, C., & Hu, X. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78495-8_26 · Cited by 1
Retrospective and Prospective Mixture-of-Generators for Task-Oriented Dialogue Response Generation
Pei, J., Ren, P., Monz, C., & de Rijke, M. (2020) · Frontiers in artificial intelligence and applications · doi:10.3233/faia200339
Khawer, M. A., Khan, S., Qureshi, R., Awais, M., Chen, W., & Wu, J. (2025) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi60581.2025.10980909
Multi-Source Domain Adaptation for Dependency Parsing via In-Depth Feature Transfer
Li, Y., Zhu, S., Liu, J., Yu, Z., & Huang, Y. (2025) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/taslpro.2025.3572796
Qu, Y., & Xu, C. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08275-1
Customizing Domain Adapters for Domain Generalization
Ji, Y., Huang, Z., Wang, H., & Lee, Y. J. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00095
Zhang, Y., Yan, R., & Han, Y. (2026) · World Wide Web · doi:10.1007/s11280-026-01423-w
EDS-Trans: energy-aware dual-scale transformer for multi-source-free domain adaptation
Yang, X., Li, H., Qu, Y., Zhang, B., & Ma, L. (2026) · Pattern Analysis and Applications · doi:10.1007/s10044-026-01767-z
Liu, Q., Schimmler, S., & Hauswirth, M. (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-026-02536-5
Metadata
- Authors
- Guo, J., Shah, D., & Barzilay, R.
- Affiliations
- MIT Computer Science and Artificial Intelligence Laboratory (US)
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 4694-4703
- OpenAlex
- W2891691791
- Cited by
- 168
- References
- 41
- Citations by year
- 2026: 4 · 2025: 11 · 2024: 19 · 2023: 24 · 2022: 29 · 2021: 37 · 2020: 27 · 2019: 17
- FWCI
- 8.27
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- multi-source domain adaptation, mixture of experts, unsupervised domain adaptation, negative transfer, sentiment analysis, part-of-speech tagging
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
