# Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approach

arXiv: https://arxiv.org/abs/2312.11276 · HTML: https://mlsanity.com/paper/2312.11276/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 18 Dec 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [Good-Enough Compositional Data Augmentation](https://mlsanity.com/paper/1904.09545/) (2019)
- [Improving Text-to-SQL Evaluation Methodology](https://mlsanity.com/paper/1806.09029/) (2018)
- [Data Recombination for Neural Semantic Parsing](https://mlsanity.com/paper/1606.03622/) (2016)
- [Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures](https://mlsanity.com/paper/2007.08970/) (2020)
- [Robustness to Spurious Correlations in Text Classification via Automatically Generated Counterfactuals](https://mlsanity.com/paper/2012.10040/) (2020)
- [Compositional generalization in a deep seq2seq model by separating syntax and semantics](https://mlsanity.com/paper/1904.09708/) (2019)
- [Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing](https://mlsanity.com/paper/2205.12253/) (2022)
- [Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution](https://mlsanity.com/paper/2109.04712/) (2021)
- [Disentangled Sequence to Sequence Learning for Compositional Generalization](https://mlsanity.com/paper/2110.04655/) (2021)
- [Few-Shot Semantic Parsing for New Predicates](https://mlsanity.com/paper/2101.10708/) (2021)
- [Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation](https://mlsanity.com/paper/2306.10317/) (2023)
- [One-Shot Learning for Text-to-SQL Generation](https://mlsanity.com/paper/1905.11499/) (2019)
- [Label-Wise Document Pre-Training for Multi-Label Text Classification](https://mlsanity.com/paper/2008.06695/) (2020)

## Built on by (most cited first, 7 of 7)

- [From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks](https://mlsanity.com/paper/2405.15164/) (2024)
- [Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations](https://mlsanity.com/paper/2412.16521/) (2024)
- [Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL](https://mlsanity.com/paper/2508.09193/) (2025)
- [A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trends](https://mlsanity.com/paper/2406.06119/) (2024)
- [Don't Pay Attention, PLANT It: Pretraining Attention via Learning-to-Rank](https://mlsanity.com/paper/2410.23066/) (2024)
- [Multi-Sourced Compositional Generalization in Visual Question Answering](https://mlsanity.com/paper/2505.23045/) (2025)
- [D2ACE: Multi-Label Batch Selection Guided by Dual Dynamics and Adaptive Correlation Enhancement](https://mlsanity.com/paper/2605.09400/) (2026)

## Abstract (arXiv)

Despite significant advancements in multi-label text classification, the ability of existing models to generalize to novel and seldom-encountered complex concepts, which are compositions of elementary ones, remains underexplored. This research addresses this gap. By creating unique data splits across three benchmarks, we assess the compositional generalization ability of existing multi-label text classification models. Our results show that these models often fail to generalize to compositional concepts encountered infrequently during training, leading to inferior performance on tests with these new combinations. To address this, we introduce a data augmentation method that leverages two innovative text generation models designed to enhance the classification models' capacity for compositional generalization. Our experiments show that this data augmentation approach significantly improves the compositional generalization capabilities of classification models on our benchmarks, with both generation models surpassing other text generation baselines.