# DA-Net: A Disentangled and Adaptive Network for Multi-Source Cross-Lingual Transfer Learning

arXiv: https://arxiv.org/abs/2403.04158 · HTML: https://mlsanity.com/paper/2403.04158/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [What makes instance discrimination good for transfer learning?](https://mlsanity.com/paper/2006.06606/) (2020)
- [Multi-Source Domain Adaptation with Mixture of Experts](https://mlsanity.com/paper/1809.02256/) (2018)
- [Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language](https://mlsanity.com/paper/2004.12440/) (2020)
- [Rethinking Supervised Pre-training for Better Downstream Transferring](https://mlsanity.com/paper/2110.06014/) (2021)
- [UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data](https://mlsanity.com/paper/2007.07683/) (2020)
- [Zero-Shot Cross-lingual Semantic Parsing](https://mlsanity.com/paper/2104.07554/) (2021)
- [AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER](https://mlsanity.com/paper/2106.02300/) (2021)
- [Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition](https://mlsanity.com/paper/2106.00241/) (2021)
- [Towards Lingua Franca Named Entity Recognition with BERT](https://mlsanity.com/paper/1912.01389/) (2019)
- [Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification](https://mlsanity.com/paper/2110.14764/) (2021)

## Abstract (arXiv)

Multi-Source cross-lingual transfer learning deals with the transfer of task knowledge from multiple labelled source languages to an unlabeled target language under the language shift. Existing methods typically focus on weighting the predictions produced by language-specific classifiers of different sources that follow a shared encoder. However, all source languages share the same encoder, which is updated by all these languages. The extracted representations inevitably contain different source languages' information, which may disturb the learning of the language-specific classifiers. Additionally, due to the language gap, language-specific classifiers trained with source labels are unable to make accurate predictions for the target language. Both facts impair the model's performance. To address these challenges, we propose a Disentangled and Adaptive Network (DA-Net). Firstly, we devise a feedback-guided collaborative disentanglement method that seeks to purify input representations of classifiers, thereby mitigating mutual interference from multiple sources. Secondly, we propose a class-aware parallel adaptation method that aligns class-level distributions for each source-target language pair, thereby alleviating the language pairs' language gap. Experimental results on three different tasks involving 38 languages validate the effectiveness of our approach.