# FOCAL-Attention for Heterogeneous Multi-Label Prediction

arXiv: https://arxiv.org/abs/2604.19171 · HTML: https://mlsanity.com/paper/2604.19171/

## 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 (most cited first, 21 of 21)

- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [KGAT: Knowledge Graph Attention Network for Recommendation](https://mlsanity.com/paper/1905.07854/) (2019)
- [MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding](https://mlsanity.com/paper/2002.01680/) (2020)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [Knowledge Graph Convolutional Networks for Recommender Systems](https://mlsanity.com/paper/1904.12575/) (2019)
- [Relational Graph Attention Networks](https://mlsanity.com/paper/1904.05811/) (2019)
- [A Comprehensive Survey on Deep Graph Representation Learning](https://mlsanity.com/paper/2304.05055/) (2023)
- [Interpretable and Efficient Heterogeneous Graph Convolutional Network](https://mlsanity.com/paper/2005.13183/) (2020)
- [HiGPT: Heterogeneous Graph Language Model](https://mlsanity.com/paper/2402.16024/) (2024)
- [Self-supervised Heterogeneous Graph Pre-training Based on Structural Clustering](https://mlsanity.com/paper/2210.10462/) (2022)
- [Correlation-Aware Graph Convolutional Networks for Multi-Label Node Classification](https://mlsanity.com/paper/2411.17350/) (2024)
- [RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendation](https://mlsanity.com/paper/2407.20684/) (2024)
- [Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification](https://mlsanity.com/paper/1907.05743/) (2019)
- [Hierarchical Contrastive Learning Enhanced Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2304.12228/) (2023)
- [Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations](https://mlsanity.com/paper/2505.23014/) (2025)
- [CITE: A Comprehensive Benchmark for Heterogeneous Text-Attributed Graphs on Catalytic Materials](https://mlsanity.com/paper/2508.15392/) (2025)

## 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.