# SSL Framework for Causal Inconsistency between Structures and Representations

arXiv: https://arxiv.org/abs/2310.18634 · HTML: https://mlsanity.com/paper/2310.18634/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 70 references that are in the map.
- First posted on arXiv 28 Oct 2023.

## Builds on (most cited first, 30 of 40)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation](https://mlsanity.com/paper/1903.01945/) (2019)
- [DAG-GNN: DAG Structure Learning with Graph Neural Networks](https://mlsanity.com/paper/1904.10098/) (2019)
- [Whitening for Self-Supervised Representation Learning](https://mlsanity.com/paper/2007.06346/) (2020)
- [Discovering Invariant Rationales for Graph Neural Networks](https://mlsanity.com/paper/2201.12872/) (2022)
- [Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changes](https://mlsanity.com/paper/1903.01672/) (2019)
- [Interventional Causal Representation Learning](https://mlsanity.com/paper/2209.11924/) (2022)
- [Causality Inspired Representation Learning for Domain Generalization](https://mlsanity.com/paper/2203.14237/) (2022)
- [Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions](https://mlsanity.com/paper/1707.06422/) (2017)
- [Causal Consistency of Structural Equation Models](https://mlsanity.com/paper/1707.00819/) (2017)
- [Abstracting Causal Models](https://mlsanity.com/paper/1812.03789/) (2018)
- [Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networks](https://mlsanity.com/paper/1708.04299/) (2017)
- [Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data](https://mlsanity.com/paper/2006.10833/) (2020)
- [Directed Acyclic Graph Network for Conversational Emotion Recognition](https://mlsanity.com/paper/2105.12907/) (2021)
- [Alleviating Over-segmentation Errors by Detecting Action Boundaries](https://mlsanity.com/paper/2007.06866/) (2020)
- [Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure](https://mlsanity.com/paper/2209.14107/) (2022)
- [Recognizing Emotion Cause in Conversations](https://mlsanity.com/paper/2012.11820/) (2020)
- [High Fidelity Image Counterfactuals with Probabilistic Causal Models](https://mlsanity.com/paper/2306.15764/) (2023)
- [Transporting Causal Mechanisms for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.11055/) (2021)
- [Invariant and Transportable Representations for Anti-Causal Domain Shifts](https://mlsanity.com/paper/2207.01603/) (2022)
- [Domain adaptation under structural causal models](https://mlsanity.com/paper/2010.15764/) (2020)
- [Coarse to Fine Multi-Resolution Temporal Convolutional Network](https://mlsanity.com/paper/2105.10859/) (2021)
- [Causal Discovery from Incomplete Data: A Deep Learning Approach](https://mlsanity.com/paper/2001.05343/) (2020)
- [Image-based Treatment Effect Heterogeneity](https://mlsanity.com/paper/2206.06417/) (2022)
- [Towards Trustworthy Explanation: On Causal Rationalization](https://mlsanity.com/paper/2306.14115/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Survey on Enhancing Causal Reasoning Ability of Large Language Models](https://mlsanity.com/paper/2503.09326/) (2025)
- [Towards Causal Relationship in Indefinite Data: Baseline Model and New Datasets](https://mlsanity.com/paper/2401.08221/) (2024)

## Abstract (arXiv)

The cross-pollination between causal discovery and deep learning has led to increasingly extensive interactions. It results in a large number of deep learning data types (such as images, text, etc.) extending into the field of causal discovery, and a multitude of deep learning tasks have begun to utilize causal discovery to explore the internal causal structure and causal representation of data. In this paper, we first identified that a complex data type, ``Indefinite Data", has conflicts between causal relationships expressed by the causal structure and causal representation generated by deep learning models, a phenomenon referred to as causal inconsistency. We thoroughly analyzed related work to explain why only Indefinite Data exhibits causal inconsistency while other data types do not. Furthermore, to alleviate causal inconsistency, we proposed a self-supervised learning (SSL) framework based on intervention, hoping to provide more causal information from different intervention views to promote consistency between structure and representation. Extensive experiments have shown that the SSL framework enhances causal consistency and can further improve causal structure and representation learning performance. Additionally, we extended the SSL framework to three different downstream tasks and LLM instructions. The quantitative results of these applications all reflect the performance improvement brought about by causal consistency.