Advanced Graph Neural Networks

Derniers papiers

• Graph VQ-Transformer (GVT): Fast and Accurate Molecular Generation via High-Fidelity Discrete Latents

  Haozhuo Zheng, Cheng Wang, Yang Liu · 3 décembre 2025

  The de novo generation of molecules with desirable properties is a critical challenge, where diffusion models are computationally intensive and autoregressive models struggle with error propagation. In this work, we introduce the Graph VQ-Transformer (GVT), a two-stage generative framework that achi…

• Conformal Correction for Efficiency May be at Odds with Entropy

  Senrong Xu, Tianyu Wang, Zenan Li, Yuan Yao, Taolue Chen, Feng Xu, Xiaoxing Ma · 3 décembre 2025

  Conformal prediction (CP) provides a comprehensive framework to produce statistically rigorous uncertainty sets for black-box machine learning models. To further improve the efficiency of CP, conformal correction is proposed to fine-tune or wrap the base model with an extra module using a conformal-…

• Embedding networks with the random walk first return time distribution

  Vedanta Thapar, Renaud Lambiotte, George T. Cantwell · 3 décembre 2025

  We propose the first return time distribution (FRTD) of a random walk as an interpretable and mathematically grounded node embedding. The FRTD assigns a probability mass function to each node, allowing us to define a distance between any pair of nodes using standard metrics for discrete distribution…

• HTG-GCL: Leveraging Hierarchical Topological Granularity from Cellular Complexes for Graph Contrastive Learning

  Qirui Ji, Bin Qin, Yifan Jin, Yunze Zhao, Chuxiong Sun, Changwen Zheng, Jianwen Cao, Jiangmeng Li · 3 décembre 2025

  Graph contrastive learning (GCL) aims to learn discriminative semantic invariance by contrasting different views of the same graph that share critical topological patterns. However, existing GCL approaches with structural augmentations often struggle to identify task-relevant topological structures,…

• FGC-Comp: Adaptive Neighbor-Grouped Attribute Completion for Graph-based Anomaly Detection

  Junpeng Wu, Pinheng Zong · 3 décembre 2025

  Graph-based Anomaly Detection models have gained widespread adoption in recent years, identifying suspicious nodes by aggregating neighborhood information. However, most existing studies overlook the pervasive issues of missing and adversarially obscured node attributes, which can undermine aggregat…

• Credal Graph Neural Networks

  Matteo Tolloso, Davide Bacciu · 3 décembre 2025

  Uncertainty quantification is essential for deploying reliable Graph Neural Networks (GNNs), where existing approaches primarily rely on Bayesian inference or ensembles. In this paper, we introduce the first credal graph neural networks (CGNNs), which extend credal learning to the graph domain by tr…

• GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace

  Miko{\l}aj Sacha, Hammad Jafri, Mattie Terzolo, Ayan Sinha, Andrew Rabinovich · 3 décembre 2025

  Recommending matches in a text-rich, dynamic two-sided marketplace presents unique challenges due to evolving content and interaction graphs. We introduce GraphMatch, a new large-scale recommendation framework that fuses pre-trained language models with graph neural networks to overcome these challe…

• Cross-View Topology-Aware Graph Representation Learning

  Ahmet Sami Korkmaz, Selim Coskunuzer, Md Joshem Uddin · 3 décembre 2025

  Graph classification has gained significant attention due to its applications in chemistry, social networks, and bioinformatics. While Graph Neural Networks (GNNs) effectively capture local structural patterns, they often overlook global topological features that are critical for robust representati…

• Elastic Weight Consolidation for Knowledge Graph Continual Learning: An Empirical Evaluation

  Gaganpreet Jhajj, Fuhua Lin · 2 décembre 2025

  Knowledge graphs (KGs) require continual updates as new information emerges, but neural embedding models suffer from catastrophic forgetting when learning new tasks sequentially. We evaluate Elastic Weight Consolidation (EWC), a regularization-based continual learning method, on KG link prediction u…

• Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves

  Alessio Borgi, Fabrizio Silvestri, Pietro Li\`o · 2 décembre 2025

  Sheaf Neural Networks equip graph structures with a cellular sheaf: a geometric structure which assigns local vector spaces (stalks) and a linear learnable restriction/transport maps to nodes and edges, yielding an edge-aware inductive bias that handles heterophily and limits oversmoothing. However,…

• The Information Theory of Similarity

  Nikit Phadke · 2 décembre 2025

  We establish a precise mathematical equivalence between witness-based similarity systems (REWA) and Shannon's information theory. We prove that witness overlap is mutual information, that REWA bit complexity bounds arise from channel capacity limitations, and that ranking-preserving encodings obey r…

• Exploring Variational Graph Autoencoders for Distribution Grid Data Generation

  Syed Zain Abbas, Ehimare Okoyomon · 2 décembre 2025

  To address the lack of public power system data for machine learning research in energy networks, we investigate the use of variational graph autoencoders (VGAEs) for synthetic distribution grid generation. Using two open-source datasets, ENGAGE and DINGO, we evaluate four decoder variants and compa…

• Generalized Graph Transformer Variational Autoencoder

  Siddhant Karki · 2 décembre 2025

  Graph link prediction has long been a central problem in graph representation learning in both network analysis and generative modeling. Recent progress in deep learning has introduced increasingly sophisticated architectures for capturing relational dependencies within graph-structured data. In thi…

• Morphling: Fast, Fused, and Flexible GNN Training at Scale

  Anubhab, Rupesh Nasre · 2 décembre 2025

  Graph Neural Networks (GNNs) present a fundamental hardware challenge by fusing irregular, memory-bound graph traversals with regular, compute-intensive dense matrix operations. While frameworks such as PyTorch Geometric (PyG) and Deep Graph Library (DGL) prioritize high-level usability, they fail t…

• Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning

  Dongyue Li, Zhenshuo Zhang, Minxuan Duan, Edgar Dobriban, Hongyang R. Zhang · 2 décembre 2025

  Algorithmic reasoning -- the ability to perform step-by-step logical inference -- has become a core benchmark for evaluating reasoning in graph neural networks (GNNs) and large language models (LLMs). Ideally, one would like to design a single model capable of performing well on multiple algorithmic…

• AEGIS: Authentic Edge Growth In Sparsity for Link Prediction in Edge-Sparse Bipartite Knowledge Graphs

  Hugh Xuechen Liu, K{\i}van\c{c} Tatar · 2 décembre 2025

  Bipartite knowledge graphs in niche domains are typically data-poor and edge-sparse, which hinders link prediction. We introduce AEGIS (Authentic Edge Growth In Sparsity), an edge-only augmentation framework that resamples existing training edges -either uniformly simple or with inverse-degree bias …

• A Method for Handling Negative Similarities in Explainable Graph Spectral Clustering of Text Documents -- Extended Version

  Mieczys{\l}aw A. K{\l}opotek, S{\l}awomir T. Wierzcho\'n, Bart{\l}omiej Starosta, Dariusz Czerski, Piotr Borkowski · 2 décembre 2025

  This paper investigates the problem of Graph Spectral Clustering with negative similarities, resulting from document embeddings different from the traditional Term Vector Space (like doc2vec, GloVe, etc.). Solutions for combinatorial Laplacians and normalized Laplacians are discussed. An experimenta…

• Graph Persistence goes Spectral

  Mattie Ji, Amauri H. Souza, Vikas Garg · 2 décembre 2025

  Including intricate topological information (e.g., cycles) provably enhances the expressivity of message-passing graph neural networks (GNNs) beyond the Weisfeiler-Leman (WL) hierarchy. Consequently, Persistent Homology (PH) methods are increasingly employed for graph representation learning. In thi…

• Hyperbolic Continuous Structural Entropy for Hierarchical Clustering

  Guangjie Zeng, Hao Peng, Angsheng Li, Li Sun, Chunyang Liu, Shengze Li, Yicheng Pan, Philip S. Yu · 2 décembre 2025

  Hierarchical clustering is a fundamental machine-learning technique for grouping data points into dendrograms. However, existing hierarchical clustering methods encounter two primary challenges: 1) Most methods specify dendrograms without a global objective. 2) Graph-based methods often neglect the …

• Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift

  Fanlong Zeng, Wensheng Gan · 2 décembre 2025

  Covariate distribution shift occurs when certain structural features present in the test set are absent from the training set. It is a common type of out-of-distribution (OOD) problem, frequently encountered in real-world graph data with complex structures. Existing research has revealed that most o…

• LGDC: Latent Graph Diffusion via Spectrum-Preserving Coarsening

  Nagham Osman, Keyue Jiang, Davide Buffelli, Xiaowen Dong, Laura Toni · 2 décembre 2025

  Graph generation is a critical task across scientific domains. Existing methods fall broadly into two categories: autoregressive models, which iteratively expand graphs, and one-shot models, such as diffusion, which generate the full graph at once. In this work, we provide an analysis of these two p…

• Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models

  Alla Chepurova, Aydar Bulatov, Yuri Kuratov, Mikhail Burtsev · 2 décembre 2025

  Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In this work, we propose Wikontic, a multi-stage pipeline that c…

• Less is More: Towards Simple Graph Contrastive Learning

  Yanan Zhao, Feng Ji, Jingyang Dai, Jiaze Ma, Wee Peng Tay · 2 décembre 2025

  Graph Contrastive Learning (GCL) has shown strong promise for unsupervised graph representation learning, yet its effectiveness on heterophilic graphs, where connected nodes often belong to different classes, remains limited. Most existing methods rely on complex augmentation schemes, intricate enco…

• Graph Distance as Surprise: Free Energy Minimization in Knowledge Graph Reasoning

  Gaganpreet Jhajj, Fuhua Lin · 2 décembre 2025

  In this work, we propose that reasoning in knowledge graph (KG) networks can be guided by surprise minimization. Entities that are close in graph distance will have lower surprise than those farther apart. This connects the Free Energy Principle (FEP) from neuroscience to KG systems, where the KG se…

• Multi-View Graph Learning with Graph-Tuple

  Shiyu Chen, Ningyuan Huang, Soledad Villar · 2 décembre 2025

  Graph Neural Networks (GNNs) typically scale with the number of graph edges, making them well suited for sparse graphs but less efficient on dense graphs, such as point clouds or molecular interactions. A common remedy is to sparsify the graph via similarity thresholding or distance pruning, but thi…