mlsanityData to 14 Oct 2026

FOCAL-Attention for Heterogeneous Multi-Label Prediction

arXiv 2604.19171 ↗First posted 21 Apr 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Heterogeneous graphs have attracted increasing attention for modeling multi-typed entities and relations in complex real-world systems. Multi-label node classification on heterogeneous graphs is challenging due to structural heterogeneity and the need to learn shared representations across multiple labels. Existing methods typically adopt either flexible attention mechanisms or meta-path constrained anchoring, but in heterogeneous multi-label prediction they often suffer from semantic dilution or coverage constraint. Both issues are further amplified under multi-label supervision. We present a theoretical analysis showing that as heterogeneous neighborhoods expand, the attention mass allocated to task-critical (primary) neighborhoods diminishes, and that meta-path constrained aggregation exhibits a dilemma: too few meta-paths intensify coverage constraint, while too many re-introduce dilution. To resolve this coverage-anchoring conflict, we propose FOCAL: Fusion Of Coverage and Anchoring Learning, with two components: coverage-oriented attention (COA) for flexible, unconstrained heterogeneous context aggregation, and anchoring-oriented attention (AOA) that restricts aggregation to meta-path-induced primary semantics. Our theoretical analysis and experimental results further indicates that FOCAL has a better performance than other state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

21 of 33 references.

References · 21

  1. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  2. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  3. 2019Heterogeneous Graph Attention Networkcited by 734
  4. 2020Heterogeneous Graph Transformercited by 582
  5. 2019Graph Transformer Networkscited by 523
  6. 2020Asymmetric Loss For Multi-Label Classificationcited by 381
  7. 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 343
  8. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  9. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  10. 2019Knowledge Graph Convolutional Networks for Recommender Systemscited by 121
  11. 2019Relational Graph Attention Networkscited by 82
  12. 2023A Comprehensive Survey on Deep Graph Representation Learningcited by 72
9 more
  1. 2020Interpretable and Efficient Heterogeneous Graph Convolutional Networkcited by 48
  2. 2024HiGPT: Heterogeneous Graph Language Modelcited by 45
  3. 2022Self-supervised Heterogeneous Graph Pre-training Based on Structural Clusteringcited by 30
  4. 2024Correlation-Aware Graph Convolutional Networks for Multi-Label Node Classificationcited by 11
  5. 2024RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendationcited by 8
  6. 2019Semi-Supervised Graph Embedding for Multi-Label Graph Node Classificationcited by 7
  7. 2023Hierarchical Contrastive Learning Enhanced Heterogeneous Graph Neural Networkcited by 6
  8. 2025Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equationscited by 2
  9. 2025CITE: A Comprehensive Benchmark for Heterogeneous Text-Attributed Graphs on Catalytic Materialscited by 1

Built on by

Not cited yet.