mlsanityData to 14 Oct 2026

Text Meets Topology: Rethinking Out-of-distribution Detection in Text-Rich Networks

arXiv 2508.17690 ↗First posted 25 Aug 2025cs.CL cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection remains challenging in text-rich networks, where textual features intertwine with topological structures. Existing methods primarily address label shifts or rudimentary domain-based splits, overlooking the intricate textual-structural diversity. For example, in social networks, where users represent nodes with textual features (name, bio) while edges indicate friendship status, OOD may stem from the distinct language patterns between bot and normal users. To address this gap, we introduce the TextTopoOOD framework for evaluating detection across diverse OOD scenarios: (1) attribute-level shifts via text augmentations and embedding perturbations; (2) structural shifts through edge rewiring and semantic connections; (3) thematically-guided label shifts; and (4) domain-based divisions. Furthermore, we propose TNT-OOD to model the complex interplay between Text aNd Topology using: 1) a novel cross-attention module to fuse local structure into node-level text representations, and 2) a HyperNetwork to generate node-specific transformation parameters. This aligns topological and semantic features of ID nodes, enhancing ID/OOD distinction across structural and textual shifts. Experiments on 11 datasets across four OOD scenarios demonstrate the nuanced challenge of TextTopoOOD for evaluating OOD detection in text-rich networks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 36 of its 56 references that are in the map. First posted on arXiv 25 Aug 2025.

Builds on

36 of 56 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  5. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  7. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  10. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  11. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  12. 2017Community Detection and Stochastic Block Modelscited by 319
24 more
  1. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 243
  2. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 141
  3. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  4. 2022Out-Of-Distribution Generalization on Graphs: A Surveycited by 97
  5. 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
  6. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 80
  7. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  8. 2024Can GNN be Good Adapter for LLMs?cited by 71
  9. 2023CaT: Balanced Continual Graph Learning with Graph Condensationcited by 52
  10. 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insightscited by 44
  11. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 42
  12. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  13. 2023Learning on Graphs with Out-of-Distribution Nodescited by 29
  14. 2024Large Language Models for Anomaly and Out-of-Distribution Detection: A Surveycited by 27
  15. 2024Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Modelscited by 22
  16. 2023Pretraining Language Models with Text-Attributed Heterogeneous Graphscited by 15
  17. 2025GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generationcited by 15
  18. 2024CaseLink: Inductive Graph Learning for Legal Case Retrievalcited by 11
  19. 2023CaseGNN: Graph Neural Networks for Legal Case Retrieval with Text-Attributed Graphscited by 9
  20. 2025Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphscited by 9
  21. 2024Hate Speech Detection with Generalizable Target-aware Fairnesscited by 7
  22. 2025Out-of-Distribution Detection on Graphs: A Surveycited by 6
  23. 2025Bounded and Uniform Energy-based Out-of-distribution Detection for Graphscited by 6
  24. 2023FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Scorecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026What Information Matters? Graph Out-of-Distribution Detection via Tri-Component Information Decompositioncited by 1
  2. 2026Call Neighbours Yourself: Graph Walks with Destination-Conditioned On-Policy Self-Distillationcited by 1
  3. 2025ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimationcited by 0