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

[Submitted on 13 Apr 2026 (v1), last revised 4 Aug 2026 (this version, v3)]

View PDF HTML (experimental)

Abstract: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.

Submission history

From: Yang Yan [view email]
[v1] Mon, 13 Apr 2026 01:03:44 UTC (2,747 KB)
[v2] Mon, 20 Jul 2026 10:42:57 UTC (2,749 KB)
[v3] Tue, 4 Aug 2026 02:27:29 UTC (3,006 KB)