# DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation

arXiv: https://arxiv.org/abs/2604.10882 · HTML: https://mlsanity.com/paper/2604.10882/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 21 of 21)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Strategies for Pre-training Graph Neural Networks](https://mlsanity.com/paper/1905.12265/) (2019)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [TUDataset: A collection of benchmark datasets for learning with graphs](https://mlsanity.com/paper/2007.08663/) (2020)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Graph Information Bottleneck](https://mlsanity.com/paper/2010.12811/) (2020)
- [Cross-Layer Distillation with Semantic Calibration](https://mlsanity.com/paper/2012.03236/) (2020)
- [GOOD: A Graph Out-of-Distribution Benchmark](https://mlsanity.com/paper/2206.08452/) (2022)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Generalizing Graph Neural Networks on Out-Of-Distribution Graphs](https://mlsanity.com/paper/2111.10657/) (2021)
- [UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs](https://mlsanity.com/paper/2402.13630/) (2024)
- [DANE: Domain Adaptive Network Embedding](https://mlsanity.com/paper/1906.00684/) (2019)
- [Non-IID Transfer Learning on Graphs](https://mlsanity.com/paper/2212.08174/) (2022)
- [Does Invariant Graph Learning via Environment Augmentation Learn Invariance?](https://mlsanity.com/paper/2310.19035/) (2023)
- [Fully-inductive Node Classification on Arbitrary Graphs](https://mlsanity.com/paper/2405.20445/) (2024)
- [On Representation Knowledge Distillation for Graph Neural Networks](https://mlsanity.com/paper/2111.04964/) (2021)
- [Pairwise Alignment Improves Graph Domain Adaptation](https://mlsanity.com/paper/2403.01092/) (2024)
- [Homophily Enhanced Graph Domain Adaptation](https://mlsanity.com/paper/2505.20089/) (2025)
- [Cross-View Graph Consistency Learning for Invariant Graph Representations](https://mlsanity.com/paper/2311.11821/) (2023)

## Abstract (arXiv)

Graph pre-training can facilitate knowledge transfer across graph datasets, but severe structural and feature shifts may cause negative transfer and adaptation-induced overwriting of reusable knowledge. We propose DIB-OD, a heterogeneous graph adaptation framework that combines a Decoupled Information Bottleneck with Online Distillation. A multiview teacher first learns a compressed, task-relevant representation, which is distilled into a transferable core branch and a complementary residual branch. Mutual-information objectives and HSIC-based dependence regularization discourage information overlap between the branches, while a confidence-aware semantic regularizer and a frozen teacher anchor reliable pretrained information during target-domain adaptation. Experiments on seven graph-classification datasets spanning chemical, biological, and social-network domains show consistent improvements over representative baselines, particularly under challenging cross-type transfer.