# Federated Natural Language Generation for Personalized Dialogue System

arXiv: https://arxiv.org/abs/2110.06419 · HTML: https://mlsanity.com/paper/2110.06419/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 13 Oct 2021.

## Builds on (most cited first, 17 of 17)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [A Persona-Based Neural Conversation Model](https://mlsanity.com/paper/1603.06155/) (2016)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [User Modeling for Task Oriented Dialogues](https://mlsanity.com/paper/1811.04369/) (2018)
- [Federated Learning of N-gram Language Models](https://mlsanity.com/paper/1910.03432/) (2019)
- [Federated User Representation Learning](https://mlsanity.com/paper/1909.12535/) (2019)
- [Pretraining Federated Text Models for Next Word Prediction](https://mlsanity.com/paper/2005.04828/) (2020)
- [Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2003.09603/) (2020)
- [A Survey on Federated Learning and its Applications for Accelerating Industrial Internet of Things](https://mlsanity.com/paper/2104.10501/) (2021)
- [Blockchain-based Federated Learning for Device Failure Detection in Industrial IoT](https://mlsanity.com/paper/2009.02643/) (2020)

## Built on by (most cited first, 5 of 5)

- [Towards Building the Federated GPT: Federated Instruction Tuning](https://mlsanity.com/paper/2305.05644/) (2023)
- [SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support](https://mlsanity.com/paper/2305.00450/) (2023)
- [FedVLN: Privacy-preserving Federated Vision-and-Language Navigation](https://mlsanity.com/paper/2203.14936/) (2022)
- [FedPC: Federated Learning for Language Generation with Personal and Context Preference Embeddings](https://mlsanity.com/paper/2210.03766/) (2022)
- [Sequence-to-sequence models in peer-to-peer learning: A practical application](https://mlsanity.com/paper/2406.02565/) (2024)

## Abstract (arXiv)

Neural conversational models have long suffered from the problem of inconsistency and lacking coherent personality. To address the issue, persona-based models capturing individual characteristics have been proposed, but they still face the dilemma of model adaption and data privacy. To break this dilemma, we propose a novel Federated Natural Language Generation (FedNLG) framework, which learns personalized representations from various dataset on distributed devices, and thus implements the personalized dialogue system efficiently and safely. FedNLG first pre-trains parameters of standard neural conversational model over a large dialogue corpus, and then fine-tune the model parameters and persona embeddings on specific datasets, in a federated manner. Thus, the model could simultaneously learn the persona embeddings in local clients and learn shared model parameters by federated aggregation, which achieves accuracyprivacy balance. By conducting extensive experiments, we demonstrate the effectiveness of our model by pre-training model over Cornell Movie-Dialogs Corpus and fine-tuning the model over two TV series dataset.