Pith. sign in

REVIEW 11 cited by

Handling Distribution Shifts on Graphs: An Invariance Perspective

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2202.02466 v5 pith:G5CZRWKU submitted 2022-02-05 cs.LG cs.AI

Qitian Wu , Hengrui Zhang , Junchi Yan , David Wipf This is my paper · ORCID
classification cs.LGcs.AI
keywords graphdatadistributionpredictionshiftscaseeermenvironment
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight. Nonetheless, current endeavors mostly focus on Euclidean data, and its formulation for graph-structured data is not clear and remains under-explored, given two-fold fundamental challenges: 1) the inter-connection among nodes in one graph, which induces non-IID generation of data points even under the same environment, and 2) the structural information in the input graph, which is also informative for prediction. In this paper, we formulate the OOD problem on graphs and develop a new invariant learning approach, Explore-to-Extrapolate Risk Minimization (EERM), that facilitates graph neural networks to leverage invariance principles for prediction. EERM resorts to multiple context explorers (specified as graph structure editers in our case) that are adversarially trained to maximize the variance of risks from multiple virtual environments. Such a design enables the model to extrapolate from a single observed environment which is the common case for node-level prediction. We prove the validity of our method by theoretically showing its guarantee of a valid OOD solution and further demonstrate its power on various real-world datasets for handling distribution shifts from artificial spurious features, cross-domain transfers and dynamic graph evolution.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Recipe for Causal Graph Regression: Confounding Effects Revisited

    cs.LG 2025-07 conditional novelty 6.0 of 10

    The paper proposes a contrastive-learning-based causal graph regression framework that explicitly models the predictive power of confounding subgraphs and achieves state-of-the-art OOD generalization on graph regressi...

  2. Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization

    cs.LG 2025-06 conditional novelty 6.0 of 10

    PrunE prunes spurious edges with a size constraint and an epsilon-probability alignment, reporting state-of-the-art graph OOD results despite a weak theoretical analysis.

  3. Rethinking Graph Out-Of-Distribution Generalization: A Learnable Random Walk Perspective

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Learnable random-walk path sampling with a kernel-density mutual information loss improves node classification under distribution shifts, outperforming prior graph OOD methods on seven benchmarks.

  4. Memory-enhanced Invariant Prompt Learning for Urban Flow Prediction under Distribution Shifts

    cs.LG 2024-12 reject novelty 6.0 of 10

    MIP uses memory-bank prompts and variance-based invariant training to improve urban flow prediction under distribution shifts on METR-LA and NYCBike1.

  5. An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks

    cs.LG 2025-05 reject novelty 5.0 of 10

    GOOD-MIA combines invariant risk minimization, a graph information bottleneck, and risk extrapolation to run membership inference attacks against graph neural networks across different data domains.

  6. Soft causal learning for generalized molecule property prediction: An environment perspective

    cs.LG 2025-05 reject novelty 5.0 of 10

    CauEMO improves molecule out-of-distribution generalization by generating chemistry-valid environment substructures, disentangling label-irrelevant environments via a graph information bottleneck, and fusing them with...

  7. Bounded and Uniform Energy-based Out-of-distribution Detection for Graphs

    cs.LG 2025-04 conditional novelty 5.0 of 10

    NODESAFE adds two logit variance penalties to GNN training, cutting FPR95 for node-level OOD detection dramatically compared with GNNSAFE on citation and social-network graphs.

  8. diffIRM: A Diffusion-Augmented Invariant Risk Minimization Framework for Spatiotemporal Prediction over Graphs

    cs.LG 2024-12 reject novelty 5.0 of 10

    diffIRM combines a causal-feature mask, a diffusion-based environment augmentor, and an invariance penalty to improve out-of-distribution spatiotemporal graph prediction on SafeGraph, PeMS04, and PeMS08.

  9. MLDGG: Meta-Learning for Domain Generalization on Graphs

    cs.LG 2024-11 conditional novelty 5.0 of 10

    MLDGG combines meta-learning with structure and representation learners to make GNNs generalize across graph domains, reporting accuracy gains over baselines on TWITCH, Facebook-100, and WebKB.

  10. Graph Neural Networks for Scalable and Transferable Node Centrality Approximation

    cs.LG 2026-07 conditional novelty 4.0 of 10

    Mixed-distribution GNN training improves transferable betweenness rankings (τ≈0.86–0.92 across families) with large inference speedups, while closeness remains highly topology-sensitive.

  11. ScaleNet: Scale Invariance Learning in Directed Graphs

    cs.LG 2024-11 reject novelty 4.0 of 10

    The paper reports state-of-the-art node classification on five of six tested datasets using multi-scale products of a directed adjacency matrix, but the claimed scale invariance is not rigorously demonstrated.

Pith tools