# Cooperative Classification and Rationalization for Graph Generalization

arXiv: https://arxiv.org/abs/2403.06239 · HTML: https://mlsanity.com/paper/2403.06239/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 10 Mar 2024.

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [Graph Random Neural Network for Semi-Supervised Learning on Graphs](https://mlsanity.com/paper/2005.11079/) (2020)
- [Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism](https://mlsanity.com/paper/2201.12987/) (2022)
- [Understanding Attention and Generalization in Graph Neural Networks](https://mlsanity.com/paper/1905.02850/) (2019)
- [Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs](https://mlsanity.com/paper/2202.05441/) (2022)
- [Invariant Rationalization](https://mlsanity.com/paper/2003.09772/) (2020)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [Causal Attention for Interpretable and Generalizable Graph Classification](https://mlsanity.com/paper/2112.15089/) (2021)
- [Out-Of-Distribution Generalization on Graphs: A Survey](https://mlsanity.com/paper/2202.07987/) (2022)
- [Size-Invariant Graph Representations for Graph Classification Extrapolations](https://mlsanity.com/paper/2103.05045/) (2021)
- [Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure](https://mlsanity.com/paper/2209.14107/) (2022)
- [Few-Shot Graph Learning for Molecular Property Prediction](https://mlsanity.com/paper/2102.07916/) (2021)
- [A Survey of Machine Learning for Computer Architecture and Systems](https://mlsanity.com/paper/2102.07952/) (2021)
- [Attention Consistency on Visual Corruptions for Single-Source Domain Generalization](https://mlsanity.com/paper/2204.13091/) (2022)
- [SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks](https://mlsanity.com/paper/2207.07888/) (2022)
- [Learning from the Best: Rationalizing Prediction by Adversarial Information Calibration](https://mlsanity.com/paper/2012.08884/) (2020)
- [Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives](https://mlsanity.com/paper/2312.13434/) (2023)

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

- [A Survey of Deep Graph Learning under Distribution Shifts: from Graph Out-of-Distribution Generalization to Adaptation](https://mlsanity.com/paper/2410.19265/) (2024)
- [Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery](https://mlsanity.com/paper/2403.07955/) (2024)
- [GraphPrompter: Multi-stage Adaptive Prompt Optimization for Graph In-Context Learning](https://mlsanity.com/paper/2505.02027/) (2025)
- [Towards Few-shot Self-explaining Graph Neural Networks](https://mlsanity.com/paper/2408.07340/) (2024)
- [Collaborative Cognitive Diagnosis with Disentangled Representation Learning for Learner Modeling](https://mlsanity.com/paper/2411.02066/) (2024)
- [Denoising Programming Knowledge Tracing with a Code Graph-based Tuning Adaptor](https://mlsanity.com/paper/2506.11107/) (2025)
- [Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning](https://mlsanity.com/paper/2604.11986/) (2026)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have achieved impressive results in graph classification tasks, but they struggle to generalize effectively when faced with out-of-distribution (OOD) data. Several approaches have been proposed to address this problem. Among them, one solution is to diversify training distributions in vanilla classification by modifying the data environment, yet accessing the environment information is complex. Besides, another promising approach involves rationalization, extracting invariant rationales for predictions. However, extracting rationales is difficult due to limited learning signals, resulting in less accurate rationales and diminished predictions. To address these challenges, in this paper, we propose a Cooperative Classification and Rationalization (C2R) method, consisting of the classification and the rationalization module. Specifically, we first assume that multiple environments are available in the classification module. Then, we introduce diverse training distributions using an environment-conditional generative network, enabling robust graph representations. Meanwhile, the rationalization module employs a separator to identify relevant rationale subgraphs while the remaining non-rationale subgraphs are de-correlated with labels. Next, we align graph representations from the classification module with rationale subgraph representations using the knowledge distillation methods, enhancing the learning signal for rationales. Finally, we infer multiple environments by gathering non-rationale representations and incorporate them into the classification module for cooperative learning. Extensive experimental results on both benchmarks and synthetic datasets demonstrate the effectiveness of C2R. Code is available at https://github.com/yuelinan/Codes-of-C2R.