82 lines
7.8 KiB
Markdown
82 lines
7.8 KiB
Markdown
## Federated Learning for NLP
|
|
This list is constantly being updated. Feel free to contribute!
|
|
|
|
|
|
### 2023
|
|
| Title | Venue | Link |
|
|
| --- | --- | --- |
|
|
| Federated Nearest Neighbor Machine Translation | ICLR | [pdf](https://arxiv.org/pdf/2302.12211.pdf), [code](https://github.com/duyichao/FedNN-MT) |
|
|
|
|
|
|
### 2022
|
|
| Title | Venue | Link |
|
|
| --- | --- | --- |
|
|
| When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods | arXiv | [pdf](https://arxiv.org/pdf/2212.10025.pdf), [code](https://github.com/iezhuozhuo/FedETuning/tree/deltaTuning) |
|
|
| FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Tasks | arXiv | [pdf](https://arxiv.org/pdf/2212.08354.pdf) |
|
|
| Federated NLP in Few-shot Scenarios | arXiv | [pdf](https://arxiv.org/pdf/2212.05974.pdf) |
|
|
| Collaborating Heterogeneous Natural Language Processing Tasks via Federated Learning | arXiv | [pdf](https://arxiv.org/pdf/2212.05789.pdf), [code](https://github.com/alibaba/FederatedScope/tree/master/federatedscope/nlp/hetero_tasks) |
|
|
| Federated Neural Topic Models | arXiv | [pdf](https://arxiv.org/pdf/2212.02269.pdf), [code](https://github.com/Nemesis1303/gFedNTM) |
|
|
| AUG-FedPrompt: Practical Few-shot Federated NLP with Data-augmented Prompts | arXiv | [pdf](https://arxiv.org/pdf/2212.00192.pdf) |
|
|
| Federated Multilingual Models for Medical Transcript Analysis | arXiv | [pdf](https://arxiv.org/pdf/2211.09722.pdf) |
|
|
| FedPC: Federated Learning for Language Generation with Personal and Context Preference Embeddings | arXiv | [pdf](https://arxiv.org/pdf/2210.03766.pdf) |
|
|
| FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning | arXiv | [pdf](https://arxiv.org/pdf/2208.12268.pdf) |
|
|
| Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices | arXiv | [pdf](https://arxiv.org/pdf/2207.08988.pdf) |
|
|
| Fair NLP Models with Differentially Private Text Encoders | arXiv | [pdf](https://arxiv.org/pdf/2205.06135.pdf), [code](https://github.com/saist1993/DPNLP) |
|
|
| FedQAS: Privacy-aware Machine Reading Comprehension with Federated Learning | arXiv | [pdf](https://arxiv.org/pdf/2202.04742.pdf), [code](https://github.com/aitmlouk/FEDn-client-FedQAS-tf) |
|
|
| A Federated Approach to Predicting Emojis in Hindi Tweets | EMNLP | [pdf](https://arxiv.org/pdf/2211.06401.pdf), [code](https://github.com/deep1401/fedmoji) |
|
|
| Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling | EMNLP | [pdf](https://arxiv.org/pdf/2204.14017.pdf) |
|
|
| Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation | EMNLP Findings | [pdf](https://arxiv.org/pdf/2210.06894.pdf) |
|
|
| Federated Continual Learning for Text Classification via Selective Inter-client Transfer | EMNLP Findings | [pdf](https://arxiv.org/pdf/2210.06101.pdf), [code](https://github.com/RaiPranav/FCL-FedSeIT) |
|
|
| Recovering Private Text in Federated Learning of Language Models | NeurIPS | [pdf](https://openreview.net/pdf?id=dqgzfhHd2-), [code](https://github.com/Princeton-SysML/FILM) |
|
|
| Federated Learning with Noisy User Feedback | NAACL | [pdf](https://aclanthology.org/2022.naacl-main.196.pdf) |
|
|
| Training Mixed-Domain Translation Models via Federated Learning | NAACL | [pdf](https://aclanthology.org/2022.naacl-main.186.pdf) |
|
|
| Pretrained Models for Multilingual Federated Learning| NAACL | [pdf](https://arxiv.org/pdf/2206.02291.pdf), [code](https://github.com/orionw/Multilingual-Federated-Learning) |
|
|
| FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks | NAACL Findings | [pdf](https://aclanthology.org/2022.findings-naacl.13.pdf), [code](https://github.com/FedML-AI/FedNLP) |
|
|
| Intrinsic Gradient Compression for Scalable and Efficient Federated Learning | ACL Workshop | [pdf](https://aclanthology.org/2022.fl4nlp-1.4.pdf) |
|
|
| Adaptive Differential Privacy for Language Model Training | ACL Workshop | [pdf](https://aclanthology.org/2022.fl4nlp-1.3.pdf), [code](https://github.com/flamewei123/ADP) |
|
|
| Scaling Language Model Size in Cross-Device Federated Learning | ACL Workshop | [pdf](https://aclanthology.org/2022.fl4nlp-1.2.pdf) |
|
|
| ActPerFL: Active Personalized Federated Learning | ACL Workshop | [pdf](https://aclanthology.org/2022.fl4nlp-1.1.pdf) |
|
|
| Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information | IJCNN | [pdf](https://arxiv.org/pdf/2205.13300.pdf) |
|
|
| Federated Split BERT for Heterogeneous Text Classification | IJCNN | [pdf](https://arxiv.org/pdf/2205.13299.pdf) |
|
|
| Federated Learning for Violence Incident Prediction in a Simulated Cross-institutional Psychiatric Setting | Expert Systems with Applications | [pdf](https://arxiv.org/pdf/2205.10234.pdf) |
|
|
| FedBERT: When Federated Learning Meets Pre-Training | TIST | [pdf](https://dl.acm.org/doi/pdf/10.1145/3510033) |
|
|
| FedKC: Federated Knowledge Composition for Multilingual Natural Language Understanding | WWW | [pdf](https://dl.acm.org/doi/pdf/10.1145/3485447.3511988) |
|
|
|
|
|
|
### 2021
|
|
| Title | Venue | Link |
|
|
| --- | --- | --- |
|
|
| FedMatch: Federated Learning Over Heterogeneous Question Answering Data | CIKM | [pdf](https://dl.acm.org/doi/pdf/10.1145/3459637.3482345), [code](https://github.com/Chriskuei/FedMatch) |
|
|
| Federated Chinese Word Segmentation with Global Character Associations | ACL Findings | [pdf](https://aclanthology.org/2021.findings-acl.376.pdf), [code](https://github.com/cuhksz-nlp/GCASeg) |
|
|
| Improving Federated Learning for Aspect-based Sentiment Analysis via Topic Memories | EMNLP | [pdf](https://aclanthology.org/2021.emnlp-main.321.pdf), [code](https://github.com/cuhksz-nlp/ASA-TM) |
|
|
| A Secure and Efficient Federated Learning Framework for NLP | EMNLP | [pdf](https://aclanthology.org/2021.emnlp-main.606.pdf) |
|
|
| Distantly Supervised Relation Extraction in Federated Settings | EMNLP Findings | [pdf](https://aclanthology.org/2021.findings-emnlp.52.pdf), [code](https://github.com/DianboWork/FedDS) |
|
|
| Scaling Federated Learning for Fine-tuning of Large Language Models | arXiv | [pdf](https://arxiv.org/pdf/2102.00875.pdf) |
|
|
|
|
|
|
### 2020
|
|
| Title | Venue | Link |
|
|
| --- | --- | --- |
|
|
| FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction | EMNLP | [pdf](https://aclanthology.org/2020.emnlp-main.165.pdf) |
|
|
| Empirical Studies of Institutional Federated Learning For Natural Language Processing | EMNLP Findings | [pdf](https://aclanthology.org/2020.findings-emnlp.55.pdf) |
|
|
| Federated Learning for Spoken Language Understanding | COLING | [pdf](https://aclanthology.org/2020.coling-main.310.pdf) |
|
|
| FedNER: Privacy-preserving Medical Named Entity Recognition with Federated Learning | arXiv | [pdf](https://arxiv.org/pdf/2003.09288.pdf) |
|
|
| Federated Pretraining and Fine Tuning of BERT Using Clinical Notes from Multiple Silos | arXiv | [pdf](https://arxiv.org/pdf/2002.08562.pdf) |
|
|
| Pretraining Federated Text Models for Next Word Prediction | arXiv | [pdf](https://arxiv.org/pdf/2005.04828.pdf), [code](https://github.com/federated-learning-experiments/fl-text-models) |
|
|
|
|
|
|
### 2019
|
|
| Title | Venue | Link |
|
|
| --- | --- | --- |
|
|
| Federated Learning of N-gram Language Models | CoNLL | [pdf](https://arxiv.org/pdf/1910.03432.pdf) |
|
|
| Learning Private Neural Language Modeling with Attentive Aggregation | IJCNN | [pdf](https://arxiv.org/pdf/1812.07108.pdf) |
|
|
| Federated Learning Of Out-Of-Vocabulary Words | arXiv | [pdf](https://arxiv.org/pdf/1903.10635.pdf) |
|
|
| Federated Learning for Emoji Prediction in a Mobile Keyboard | arXiv | [pdf](https://arxiv.org/pdf/1906.04329.pdf) |
|
|
|
|
|
|
### 2018
|
|
| Title | Venue | Link |
|
|
| --- | --- | --- |
|
|
| Federated Learning for Mobile Keyboard Prediction | arXiv | [pdf](https://arxiv.org/pdf/1811.03604.pdf) |
|
|
| Applied Federated Learning: Improving Google Keyboard Query Suggestions | arXiv | [pdf](https://arxiv.org/pdf/1812.02903.pdf) |
|