HyperLabel: Multi-Label Classification via Hypergraph-Based Label Correlation Modeling

Peiyu Zhang; Heng Ping; Nikos Kanakaris; Yucheng Zhao; Shixuan Li; Wei Yang; Xiongye Xiao; Paul Bogdan

cs.LGSep 26, 2026

HyperLabel: Multi-Label Classification via Hypergraph-Based Label Correlation Modeling

Authors: Peiyu Zhang, Heng Ping, Nikos Kanakaris, Yucheng Zhao, Shixuan Li, Wei Yang, Xiongye Xiao, Paul Bogdan

Organizations: University of Southern California · Amazon Web Services · Amazon, AWS · University of Tennessee, Knoxville

Abstract

Multi-label classification (MLC) requires predicting multiple relevant labels for each instance, where a central challenge is modeling complex label dependencies arising from co-occurrence patterns. Existing approaches are limited in capturing high-order label correlations, relying on implicit learning through contrastive objectives or pairwise attention mechanisms without structural guidance. We propose HyperLabel, an encoder-decoder framework that explicitly models label dependencies through hypergraph neural networks. Our contributions are twofold: (i) We construct a label hypergraph where sample-defined hyperedges naturally encode multi-way co-occurrence patterns, providing explicit structural prior knowledge that captures relationships beyond pairwise interactions. (ii) We propose a unified cross-modal learning approach where HGNN+ performs bidirectional message passing to integrate feature information with label structure, and a shared cross-attention decoder processes both modalities through complementary learning objectives. Extensive experiments on seven benchmark datasets demonstrate that HyperLabel achieves state-of-the-art performance, with particularly significant improvements on macro-F1 scores (+10.3% on Delicious, +8.2% on Bibtex), validating that explicit hypergraph structure effectively captures complex label relationships. The code is available at https://github.com/iZHpy/Multi-label_hypergraph .

Figures & tables

Figure 1: Hypergraph construction process. Label nodes

\mathcal{V}=\{1,2,\ldots,L\}

are connected by sample-defined hyperedges. Each sample’s positive label set

\mathcal{P}(\mathbf{y}_{i})

defines a hyperedge (e.g.,

e_{1}^{*}=\{1,5,8\}

). Duplicate hyperedges are merged and assigned weights

w_{k}

based on occurrence frequency. The resulting hypergraph explicitly encodes multi-way label co-occurrence patterns.

Figure 2: Overview of HyperLabel framework. Labels are encoded via HGNN+ with hypergraph message passing, while features pass through a Transformer encoder. Aggregated label embeddings are aligned with feature embeddings and both are processed by a shared cross-attention decoder to produce label predictions

\hat{y}_{ij}

and reconstructed predictions

\hat{y}_{ij}^{\text{recon}}

Dataset	#Samples	#Features	#Labels	Card.	Density	Domain
Yeast	2,417	103	14	4.24	0.303	Biology
Scene	2,407	294	6	1.07	0.178	Vision
SIDER	1,427	27	27	15.30	0.567	Medical
Reuters	10,789	23,662	90	1.23	0.014	Text
Bibtex	7,395	1,836	159	2.40	0.015	Bibliography
Bookmarks	87,856	2,150	208	2.03	0.010	Social Tagging

Table 1: Statistics of benchmark datasets. Cardinality denotes the average number of labels per sample, and Density represents the ratio of positive labels to total possible labels.

Dataset	bibtex			sider			bookmarks
Metric	ebF1	miF1	maF1	ebF1	miF1	maF1	ebF1	miF1	maF1
w/o HGNN+	0.426	0.449	0.354	0.767	0.797	0.665	0.366	0.360	0.273
HGNN+ $\rightarrow$ GNN	0.424	0.458	0.362	0.766	0.799	0.665	0.383	0.376	0.293
Transformer $\rightarrow$ MLP	0.418	0.444	0.364	0.765	0.796	0.665	0.384	0.377	0.285
Decoupled Decoder	0.424	0.460	0.350	0.768	0.801	0.667	0.374	0.374	0.278
HyperLabel	0.433	0.462	0.370	0.772	0.805	0.668	0.390	0.383	0.302

Table 3: Ablation study results on selected datasets.

Figure 3: Learned correlations in HyperLabel on a Reuters sample. Top : feature-label correlation map. Bottom : label-label correlation map.

Multi-Label Classification

Multi-label classification assigns several potentially related tags to each example, from medical findings and topics to objects and user interests.

See all 137 papers

LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification
Sep 11, 2026Hui Ye, Jing Zhang, Xiulong Yang +1Late Fusion Multi-Label Classification
Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA · Amazon, San Diego, CA, USA · School of Computer Science, Central China Normal University, Wuhan 430079, China
Multi-Label Node Classification with Label Influence Propagation
Jul 1, 2026Yifei Sun, Zemin Liu, Bryan Hooi +4Graph-Based Label Propagation Multi-Label Classification
Zhejiang University · National University of Singapore · Capital One +1
FOCAL-Attention for Heterogeneous Multi-Label Prediction
Apr 21, 2026Chenghao Zhang, Qingqing Long, Ludi Wang +3Graph Attention Networks Multi-Label Classification
Computer Network Information Center, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China

Sep 11, 2026J/K move · Enter open · S save

LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification

Hui Ye, Jing Zhang, Xiulong Yang, Rajshekhar Sunderraman

Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA · Amazon, San Diego, CA, USA · School of Computer Science, Central China Normal University, Wuhan 430079, China

Late Fusion Multi-Label Classification Language Model Ensembles Large Language Model-Based Text Classification

Open paper AskPDF arXiv

Large-scale multi-label text classification assigns a small subset of relevant labels to each document from a vocabulary containing thousands or tens of thousands of candidate labels. Although pretrained language models have improved semantic text representations, most representation-based approaches center their prediction pipelines on a primary encoder or combine auxiliary features within a single ranker. The complementarity between heterogeneous language models therefore remains insufficiently explored. We propose DualMLC, a dual-branch framework that processes the same document through an autoregressive decoder-only language model and a bidirectional encoder. Each branch maintains its own representation pathway and independently estimates relevance scores over the shared label space. DualMLC combines the two score vectors through late logit fusion, allowing shared evidence to reinforce relevant labels and branch-specific evidence to compensate for limitations in the other branch's representation. DualMLC achieves state-of-the-art results on three widely used large-scale multi-label text classification benchmarks. Ablation results further confirm that integrating the heterogeneous predictors produces stronger rankings than either branch alone. The source code is publicly available at https://github.com/huiyegit/DualMLC.

Abstract

Multi-Label Classification

Explore similar work

LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification

Multi-Label Node Classification with Label Influence Propagation

FOCAL-Attention for Heterogeneous Multi-Label Prediction