Advanced Graph Neural Networks

Derniers papiers

• From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures

  Florian Rottach, William Rudman, Bastain Rieck, Harrisen Scells, Carsten Eickhoff · 1 décembre 2025

  Studying how embeddings are organized in space not only enhances model interpretability but also uncovers factors that drive downstream task performance. In this paper, we present a comprehensive analysis of topological and geometric measures across a wide set of text embedding models and datasets. …

• Multi-chain Graph Refinement and Selection for Reliable Reasoning in Large Language Models

  Yujiao Yang, Jing Lian, Linhui Li · 1 décembre 2025

  The complex reasoning ability of Large Language Models (LLMs) poses a critical bottleneck for their practical applications. Test-time expansion methods such as Tree-of-Thought (ToT) and Graph-of-Thought (GoT) enhance reasoning by introducing intermediate reasoning structures, tree search, or graph-b…

• IVGAE: Handling Incomplete Heterogeneous Data with a Variational Graph Autoencoder

  Youran Zhou, Mohamed Reda Bouadjenek, Sunil Aryal% · 1 décembre 2025

  Handling missing data remains a fundamental challenge in real-world tabular datasets, especially when data are heterogeneous with both numerical and categorical features. Existing imputation methods often fail to capture complex structural dependencies and handle heterogeneous data effectively. We p…

• Counting Still Counts: Understanding Neural Complex Query Answering Through Query Relaxation

  Yannick Brunink, Daniel Daza, Yunjie He, Michael Cochez · 1 décembre 2025

  Neural methods for Complex Query Answering (CQA) over knowledge graphs (KGs) are widely believed to learn patterns that generalize beyond explicit graph structure, allowing them to infer answers that are unreachable through symbolic query processing. In this work, we critically examine this assumpti…

• ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining

  Bharat Sharman, Elkafi Hassini · 1 décembre 2025

  Numerous graph neural network (GNN)-based algorithms have been proposed to solve graph-based combinatorial optimization problems (COPs), but methods to explain their predictions remain largely undeveloped. We introduce ARM-Explainer, a post-hoc, model-level explainer based on association rule mining…

• A Theoretical Framework for Discovering Groups and Unitary Representations via Tensor Factorization

  Dongsung Huh, Halyun Jeong · 1 décembre 2025

  We analyze the HyperCube model, an \textit{operator-valued} tensor factorization architecture that discovers group structures and their unitary representations. We provide a rigorous theoretical explanation for this inductive bias by decomposing its objective into a term regulating factor scales ($\…

• ResearchArcade: Graph Interface for Academic Tasks

  Jingjun Xu, Chongshan Lin, Haofei Yu, Tao Feng, Jiaxuan You · 1 décembre 2025

  Academic research generates diverse data sources, and as researchers increasingly use machine learning to assist research tasks, a crucial question arises: Can we build a unified data interface to support the development of machine learning models for various academic tasks? Models trained on such a…

• PISA: Prioritized Invariant Subgraph Aggregation

  Ali Ghasemi, Farooq Ahmad Wani, Maria Sofia Bucarelli, Fabrizio Silvestri · 1 décembre 2025

  Recent work has extended the invariance principle for out-of-distribution (OOD) generalization from Euclidean to graph data, where challenges arise due to complex structures and diverse distribution shifts in node attributes and topology. To handle these, Chen et al. proposed CIGA (Chen et al., 2022…

• Intelligent Neural Networks: From Layered Architectures to Graph-Organized Intelligence

  Antoine Salomon · 1 décembre 2025

  Biological neurons exhibit remarkable intelligence: they maintain internal states, communicate selectively with other neurons, and self-organize into complex graphs rather than rigid hierarchical layers. What if artificial intelligence could emerge from similarly intelligent computational units? We …

• A Multiscale Geometric Method for Capturing Relational Topic Alignment

  Conrad D. Hougen, Karl T. Pazdernik, Alfred O. Hero · 1 décembre 2025

  Interpretable topic modeling is essential for tracking how research interests evolve within co-author communities. In scientific corpora, where novelty is prized, identifying underrepresented niche topics is particularly important. However, contemporary models built from dense transformer embeddings…

• Representation Integrity in Temporal Graph Learning Methods

  Elahe Kooshafar · 27 novembre 2025

  Real-world systems ranging from airline routes to cryptocurrency transfers are naturally modelled as dynamic graphs whose topology changes over time. Conventional benchmarks judge dynamic-graph learners by a handful of task-specific scores, yet seldom ask whether the embeddings themselves remain a t…

• Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning

  Kaifeng Hong, Yinglong Zhang, Xiaoying Hong, Xuewen Xia, Xing Xu · 27 novembre 2025

  Text-attributed graphs require models to effectively combine strong textual understanding with structurally informed reasoning. Existing approaches either rely on GNNs--limited by over-smoothing and hop-dependent diffusion--or employ Transformers that overlook graph topology and treat nodes as isola…

• The Structure-Content Trade-off in Knowledge Graph Retrieval

  Valentin Six, Evan Dufraisse, Ga\"el de Chalendar · 27 novembre 2025

  Large Language Models (LLMs) increasingly rely on knowledge graphs for factual reasoning, yet how retrieval design shapes their performance remains unclear. We examine how question decomposition changes the retrieved subgraph's content and structure. Using a hybrid retrieval function that controls t…

• Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring

  Melika Ayoughi, Pascal Mettes, Paul Groth · 27 novembre 2025

  Hyperbolic geometry is an effective geometry for embedding hierarchical data structures. Hyperbolic learning has therefore become increasingly prominent in machine learning applications where data is hierarchically organized or governed by hierarchical semantics, ranging from recommendation systems …

• Learning Multi-Order Block Structure in Higher-Order Networks

  Kazuki Nakajima, Yuya Sasaki, Takeaki Uno, Masaki Aida · 27 novembre 2025

  Higher-order networks, naturally described as hypergraphs, are essential for modeling real-world systems involving interactions among three or more entities. Stochastic block models offer a principled framework for characterizing mesoscale organization, yet their extension to hypergraphs involves a …

• Short-Range Oversquashing

  Yaaqov Mishayev, Yonatan Sverdlov, Tal Amir, Nadav Dym · 26 novembre 2025

  Message Passing Neural Networks (MPNNs) are widely used for learning on graphs, but their ability to process long-range information is limited by the phenomenon of oversquashing. This limitation has led some researchers to advocate Graph Transformers as a better alternative, whereas others suggest t…

• Neural Tractability via Structure: Learning-Augmented Algorithms for Graph Combinatorial Optimization

  Jialiang Li, Weitong Chen, Mingyu Guo · 26 novembre 2025

  Neural models have shown promise in solving NP-hard graph combinatorial optimization (CO) problems. Once trained, they offer fast inference and reasonably high-quality solutions for in-distribution testing instances, but they generally fall short in terms of absolute solution quality compared to cla…

• Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization

  Haoran Zheng, Renchi Yang, Yubo Zhou, Jianliang Xu · 26 novembre 2025

  Message passing neural networks (MPNNs) have emerged as go-to models for learning on graph-structured data in the past decade. Despite their effectiveness, most of such models still incur severe issues such as over-smoothing and -correlation, due to their underlying objective of minimizing the Diric…

• Cross-Contrastive Clustering for Multimodal Attributed Graphs with Dual Graph Filtering

  Haoran Zheng, Renchi Yang, Hongtao Wang, Jianliang Xu · 26 novembre 2025

  Multimodal Attributed Graphs (MMAGs) are an expressive data model for representing the complex interconnections among entities that associate attributes from multiple data modalities (text, images, etc.). Clustering over such data finds numerous practical applications in real scenarios, including so…

• Decoupling and Damping: Structurally-Regularized Gradient Matching for Multimodal Graph Condensation

  Lian Shen, Zhendan Chen, Yinhui jiang, Meijia Song, Ziming Su, Juan Liu, Xiangrong Liu · 26 novembre 2025

  In critical web applications such as e-commerce and recommendation systems, multimodal graphs integrating rich visual and textual attributes are increasingly central, yet their large scale introduces substantial computational burdens for training Graph Neural Networks (GNNs). While Graph Condensatio…

• E2E-GRec: An End-to-End Joint Training Framework for Graph Neural Networks and Recommender Systems

  Rui Xue, Shichao Zhu, Liang Qin, Guangmou Pan, Yang Song, Tianfu Wu · 26 novembre 2025

  Graph Neural Networks (GNNs) have emerged as powerful tools for modeling graph-structured data and have been widely used in recommender systems, such as for capturing complex user-item and item-item relations. However, most industrial deployments adopt a two-stage pipeline: GNNs are first pre-traine…

• Rethinking Semi-Supervised Node Classification with Self-Supervised Graph Clustering

  Songbo Wang, Renchi Yang, Yurui Lai, Xiaoyang Lin, Tsz Nam Chan · 26 novembre 2025

  The emergence of graph neural networks (GNNs) has offered a powerful tool for semi-supervised node classification tasks. Subsequent studies have achieved further improvements through refining the message passing schemes in GNN models or exploiting various data augmentation techniques to mitigate lim…

• Graph Kernel Neural Networks

  Luca Cosmo, Giorgia Minello, Alessandro Bicciato, Michael Bronstein, Emanuele Rodol\`a, Luca Rossi, Andrea Torsello · 26 novembre 2025

  The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an input matrix and a filter. While this is readily applicable to data such as images, which can be represented as regular grids in the Euclidean space, extending the …

• SCNode: Spatial and Contextual Coordinates for Graph Representation Learning

  Md Joshem Uddin, Astrit Tola, Varin Sikand, Cuneyt Gurcan Akcora, Baris Coskunuzer · 26 novembre 2025

  Effective node representation lies at the heart of Graph Neural Networks (GNNs), as it directly impacts their ability to perform downstream tasks such as node classification and link prediction. Most existing GNNs, particularly message passing graph neural networks, rely on neighborhood aggregation …

• Towards Multimodal Graph Large Language Model

  Xin Wang, Zeyang Zhang, Linxin Xiao, Haibo Chen, Chendi Ge, Wenwu Zhu · 26 novembre 2025

  Multi-modal graphs, which integrate diverse multi-modal features and relations, are ubiquitous in real-world applications. However, existing multi-modal graph learning methods are typically trained from scratch for specific graph data and tasks, failing to generalize across various multi-modal graph…