DSBD distills a dual-aligned structural basis to adapt GNNs across graphs with structural distribution shifts, outperforming prior methods on benchmarks.
Discovering invariant rationales for graph neural networks
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.LG 6years
2026 6verdicts
UNVERDICTED 6roles
dataset 1polarities
use dataset 1representative citing papers
HPME proposes hard-perturbation mixup explainer grounded in generalized Graph Information Bottleneck to extract discrete subgraphs and generate in-distribution explanations that outperform soft-mask approaches on synthetic and real datasets.
B-cos GNNs replace non-linear message and update functions with B-cos transforms in GNNs to enable exact per-node per-feature explanations from a single forward-backward pass while retaining competitive accuracy.
CHCL aligns a Cheeger-Hodge joint signature across graph augmentations to produce embeddings that remain stable under local structural changes.
RIA uses adversarial exploration of counterfactual graph environments via label-invariant augmentations to improve OoD generalization in graph classification tasks.
Artemis is a region-level causal framework that learns lightweight region-specific confounder representations to adjust multimodal fMRI and DTI brain networks for demographic factors as a GNN-compatible module.
citing papers explorer
-
DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation
DSBD distills a dual-aligned structural basis to adapt GNNs across graphs with structural distribution shifts, outperforming prior methods on benchmarks.
-
Beyond Soft Masks: Hard-Perturbation Mixup Explainer for Robust GNN Explainability
HPME proposes hard-perturbation mixup explainer grounded in generalized Graph Information Bottleneck to extract discrete subgraphs and generate in-distribution explanations that outperform soft-mask approaches on synthetic and real datasets.
-
B-cos GNNs: Faithful Explanations through Dynamic Linearity
B-cos GNNs replace non-linear message and update functions with B-cos transforms in GNNs to enable exact per-node per-feature explanations from a single forward-backward pass while retaining competitive accuracy.
-
Cheeger--Hodge Contrastive Learning for Structurally Robust Graph Representation Learning
CHCL aligns a Cheeger-Hodge joint signature across graph augmentations to produce embeddings that remain stable under local structural changes.
-
Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization
RIA uses adversarial exploration of counterfactual graph environments via label-invariant augmentations to improve OoD generalization in graph classification tasks.
-
Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS
Artemis is a region-level causal framework that learns lightweight region-specific confounder representations to adjust multimodal fMRI and DTI brain networks for demographic factors as a GNN-compatible module.