From Graphs to Hypergraphs: Enhancing Aspect-Based Sentiment Analysis via Multi-Level Relational Modeling

• URL: http://arxiv.org/abs/2511.14142v1
• Date: Tue, 18 Nov 2025 05:01:25 GMT
• Title: From Graphs to Hypergraphs: Enhancing Aspect-Based Sentiment Analysis via Multi-Level Relational Modeling
• Authors: Omkar Mahesh Kashyap, Padegal Amit, Madhav Kashyap, Ashwini M Joshi, Shylaja SS,
• Abstract summary: We present HyperABSA, a dynamic hypergraph framework that induces aspect-opinion structures through sample-specific hierarchical clustering.<n>Experiments on three benchmarks show consistent improvements over strong graph baselines, with substantial gains when paired with RoBERTa backbones.
• Score: 0.04349640169711269
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aspect-Based Sentiment Analysis (ABSA) predicts sentiment polarity for specific aspect terms, a task made difficult by conflicting sentiments across aspects and the sparse context of short texts. Prior graph-based approaches model only pairwise dependencies, forcing them to construct multiple graphs for different relational views. These introduce redundancy, parameter overhead, and error propagation during fusion, limiting robustness in short-text, low-resource settings. We present HyperABSA, a dynamic hypergraph framework that induces aspect-opinion structures through sample-specific hierarchical clustering. To construct these hyperedges, we introduce a novel acceleration-fallback cutoff for hierarchical clustering, which adaptively determines the level of granularity. Experiments on three benchmarks (Lap14, Rest14, MAMS) show consistent improvements over strong graph baselines, with substantial gains when paired with RoBERTa backbones. These results position dynamic hypergraph construction as an efficient, powerful alternative for ABSA, with potential extensions to other short-text NLP tasks.

Related papers

• OTESGN: Optimal Transport-Enhanced Syntactic-Semantic Graph Networks for Aspect-Based Sentiment Analysis [5.444885665589783]
  Aspect-based sentiment analysis aims to identify aspect terms and determine their sentiment polarity.<n>We propose the Optimal Transport-Enhanced Syntactic-Semantic Graph Network (OTESGN), a model that jointly integrates structural and distributional signals.
  arXiv  Detail & Related papers  (2025-09-10T14:08:58Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Lower Ricci Curvature for Hypergraphs [3.9965784551765697]
  We introduce hypergraph lower curvature (HLRC), a novel curvature metric defined in closed form that achieves a principled balance between interpretability and efficiency.<n>HLRC consistently reveals meaningful higher-order organization, distinguishing intra-community hyperedges, uncovering latent semantic labels, tracking temporal dynamics, and supporting robust clustering of hypergraphs based on global structure.
  arXiv  Detail & Related papers  (2025-06-04T13:32:09Z)
• Feature-aware Hypergraph Generation via Next-Scale Prediction [19.753935142573507]
  We introduce FAHNES (feature-aware hypergraph generation via next-scale prediction), a hierarchical framework that jointly generates hypergraph topology and features.<n> Experiments on synthetic, 3D mesh and graph point cloud datasets show that FAHNES achieves state-of-the-art performance in jointly generating features and structure.
  arXiv  Detail & Related papers  (2025-06-02T09:24:08Z)
• HyperGCL: Multi-Modal Graph Contrastive Learning via Learnable Hypergraph Views [6.17062506211443]
  Graph Contrastive Learning (GCL) has demonstrated remarkable effectiveness in improving graph representations.<n>In this paper, we introduce HyperGCL, a novel multimodal GCL framework from a hypergraph perspective.
  arXiv  Detail & Related papers  (2025-02-18T20:57:56Z)
• Beyond Message Passing: Neural Graph Pattern Machine [50.78679002846741]
  We introduce the Neural Graph Pattern Machine (GPM), a novel framework that bypasses message passing by learning directly from graph substructures.<n>GPM efficiently extracts, encodes, and prioritizes task-relevant graph patterns, offering greater expressivity and improved ability to capture long-range dependencies.
  arXiv  Detail & Related papers  (2025-01-30T20:37:47Z)
• HyperQuery: Beyond Binary Link Prediction [0.7100520098029438]
  We introduce a novel feature extraction technique using node level clustering and show how integrating data from node-level labels can improve system performance.<n>Our self-supervised approach achieves significant improvement over state of the art baselines on several hyperedge prediction and knowledge hypergraph completion benchmarks.
  arXiv  Detail & Related papers  (2025-01-13T22:46:24Z)
• LAMP: Learnable Meta-Path Guided Adversarial Contrastive Learning for Heterogeneous Graphs [22.322402072526927]
  Heterogeneous Graph Contrastive Learning (HGCL) usually requires pre-defined meta-paths. textsfLAMP integrates various meta-path sub-graphs into a unified and stable structure. textsfLAMP significantly outperforms existing state-of-the-art unsupervised models in terms of accuracy and robustness.
  arXiv  Detail & Related papers  (2024-09-10T08:27:39Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design [6.993718963663415]
  We introduce a novel conceptualization of homophily in higher-order networks based on a Message Passing scheme.<n>We investigate some natural, yet mostly unexplored, strategies for processing higher-order structures within HNNs.
  arXiv  Detail & Related papers  (2023-10-11T17:35:20Z)
• Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning [78.49090351193269]
  We propose a novel graph-based framework to leverage the inter-relationships among different types of nuclei for WSI analysis. Specifically, we formulate the WSI as a heterogeneous graph with "nucleus-type" attribute to each node and a semantic attribute similarity to each edge. Our framework outperforms the state-of-the-art methods with considerable margins on various tasks.
  arXiv  Detail & Related papers  (2023-07-09T14:43:40Z)
• From Hypergraph Energy Functions to Hypergraph Neural Networks [94.88564151540459]
  We present an expressive family of parameterized, hypergraph-regularized energy functions. We then demonstrate how minimizers of these energies effectively serve as node embeddings. We draw parallels between the proposed bilevel hypergraph optimization, and existing GNN architectures in common use.
  arXiv  Detail & Related papers  (2023-06-16T04:40:59Z)
• Spatial-spectral Hyperspectral Image Classification via Multiple Random Anchor Graphs Ensemble Learning [88.60285937702304]
  This paper proposes a novel spatial-spectral HSI classification method via multiple random anchor graphs ensemble learning (RAGE) Firstly, the local binary pattern is adopted to extract the more descriptive features on each selected band, which preserves local structures and subtle changes of a region. Secondly, the adaptive neighbors assignment is introduced in the construction of anchor graph, to reduce the computational complexity.
  arXiv  Detail & Related papers  (2021-03-25T09:31:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.