# Multinomial Adversarial Networks for Multi-Domain Text Classification

arXiv: https://arxiv.org/abs/1802.05694 · HTML: https://mlsanity.com/paper/1802.05694/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2018.

## Built on by (most cited first, 30 of 40)

- [Modular Deep Learning](https://mlsanity.com/paper/2302.11529/) (2023)
- [Multi-Source Domain Adaptation with Mixture of Experts](https://mlsanity.com/paper/1809.02256/) (2018)
- [PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains](https://mlsanity.com/paper/2102.12206/) (2021)
- [Conditional Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/2102.10176/) (2021)
- [Modality-Agnostic Debiasing for Single Domain Generalization](https://mlsanity.com/paper/2303.07123/) (2023)
- [Mixup Regularized Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/2102.00467/) (2021)
- [Adversarial Multi-task Learning for End-to-end Metaphor Detection](https://mlsanity.com/paper/2305.16638/) (2023)
- [Multi-Domain Active Learning: Literature Review and Comparative Study](https://mlsanity.com/paper/2106.13516/) (2021)
- [Unsupervised Domain Adaptation for Hate Speech Detection Using a Data Augmentation Approach](https://mlsanity.com/paper/2107.12866/) (2021)
- [A Robust Contrastive Alignment Method For Multi-Domain Text Classification](https://mlsanity.com/paper/2204.12125/) (2022)
- [Learning to Share by Masking the Non-shared for Multi-domain Sentiment Classification](https://mlsanity.com/paper/2104.08480/) (2021)
- [Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chains](https://mlsanity.com/paper/2109.08722/) (2021)
- [Co-Regularized Adversarial Learning for Multi-Domain Text Classification](https://mlsanity.com/paper/2201.12796/) (2022)
- [Maximum Batch Frobenius Norm for Multi-Domain Text Classification](https://mlsanity.com/paper/2202.00537/) (2022)
- [Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis](https://mlsanity.com/paper/2402.14536/) (2024)
- [UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation](https://mlsanity.com/paper/2405.01022/) (2024)
- [Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation](https://mlsanity.com/paper/2108.06583/) (2021)
- [KnowMAN: Weakly Supervised Multinomial Adversarial Networks](https://mlsanity.com/paper/2109.07994/) (2021)
- [Towards More Robust Natural Language Understanding](https://mlsanity.com/paper/2112.02992/) (2021)
- [A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Ranking](https://mlsanity.com/paper/2210.15147/) (2022)
- [Preliminary Steps Towards Federated Sentiment Classification](https://mlsanity.com/paper/2107.11956/) (2021)
- [Improving Cause-of-Death Classification from Verbal Autopsy Reports](https://mlsanity.com/paper/2210.17161/) (2022)
- [MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts](https://mlsanity.com/paper/2211.13896/) (2022)
- [Multi-Domain Learning From Insufficient Annotations](https://mlsanity.com/paper/2305.02757/) (2023)
- [Out-of-Distribution Generalization in Text Classification: Past, Present, and Future](https://mlsanity.com/paper/2305.14104/) (2023)
- [Perturbation-Based Two-Stage Multi-Domain Active Learning](https://mlsanity.com/paper/2306.10700/) (2023)
- [Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting](https://mlsanity.com/paper/2402.03758/) (2024)
- [Margin Discrepancy-based Adversarial Training for Multi-Domain Text Classification](https://mlsanity.com/paper/2403.00888/) (2024)
- [Stochastic Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/2406.00044/) (2024)
- [A Unified Data Augmentation Framework for Low-Resource Multi-Domain Dialogue Generation](https://mlsanity.com/paper/2406.09881/) (2024)

## Abstract (arXiv)

Many text classification tasks are known to be highly domain-dependent. Unfortunately, the availability of training data can vary drastically across domains. Worse still, for some domains there may not be any annotated data at all. In this work, we propose a multinomial adversarial network (MAN) to tackle the text classification problem in this real-world multidomain setting (MDTC). We provide theoretical justifications for the MAN framework, proving that different instances of MANs are essentially minimizers of various f-divergence metrics (Ali and Silvey, 1966) among multiple probability distributions. MANs are thus a theoretically sound generalization of traditional adversarial networks that discriminate over two distributions. More specifically, for the MDTC task, MAN learns features that are invariant across multiple domains by resorting to its ability to reduce the divergence among the feature distributions of each domain. We present experimental results showing that MANs significantly outperform the prior art on the MDTC task. We also show that MANs achieve state-of-the-art performance for domains with no labeled data.