Advanced Graph Neural Networks

Derniers papiers

• Trees to Flows and Back: Unifying Decision Trees and Diffusion Models

  Sai Niranjan Ramachandran, Suvrit Sra · 4 mai 2026

  Decision trees and diffusion models are ostensibly disparate model classes, one discrete and hierarchical, the other continuous and dynamic. This work unifies the two by establishing a crisp mathematical correspondence between hierarchical decision trees and diffusion processes in appropriate limiti…

• Advancing Edge Classification through High-Dimensional Causal Modeling of Node-Edge Interplay

  Duanyu Feng, Li Ding, Hongru Liang, Wenqiang Lei · 4 mai 2026

  Edge classification, a crucial task for graph applications, remains relatively under-explored compared to link prediction. Current methods often overlook the potential causal influences of node features on edge features, leading to a loss of relevant prior information. In this work, we present an em…

• CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

  Weifei Jin, Xilong Wang, Wei Zou, Jinyuan Jia, Neil Gong · 4 mai 2026

  Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into the knowledge database. When a user issues a question targeted by the attack, the RAG system may retrieve these malicio…

• Adaptive Node Feature Selection For Graph Neural Networks

  Ali Azizpour, Madeline Navarro, Santiago Segarra · 4 mai 2026

  We propose an adaptive node feature selection approach for graph neural networks (GNNs) that identifies and removes unnecessary features during training. The ability to measure how features contribute to model output is key for interpreting decisions and reducing dimensionality by eliminating unhelp…

• Information-geometric adaptive sampling for graph diffusion

  Yuhui Lu, Wenjing Liu, Kun Zhan · 4 mai 2026

  Standard diffusion models for graph generation typically rely on uniform time-stepping, an approach that overlooks the non-homogeneous dynamics of distributional evolution on complex manifolds. In this paper, we present an information-geometric framework that reinterprets the diffusion sampling traj…

• Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment

  Ziyu Zheng, Yaming Yang, Zhe Wang, Ziyu Guan, Wei Zhao · 4 mai 2026

  While Graph Foundation Models (GFMs) have achieved remarkable success in homogeneous graphs, extending them to multi-domain heterogeneous graphs (MDHGs) remains a formidable challenge due to cross-type feature shifts and intra-domain relation gaps. Existing global feature alignment methods (PCA or S…

• Aitchison Embeddings for Learning Compositional Graph Representations

  Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas, Michail Chatzianastasis, Giannis Nikolentzos · 4 mai 2026

  Representation learning is central to graph machine learning, powering tasks such as link prediction and node classification. However, most graph embeddings are hard to interpret, offering limited insight into how learned features relate to graph structure. Many networks naturally admit a role-mixtu…

• When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected

  Haotian Xu, Yuning You, Tengfei Ma · 4 mai 2026

  Graphs provide a unified representation of semantic content and relational structure, making them a natural fit for domains such as molecular modeling, citation networks, and social graphs. Meanwhile, large language models (LLMs) have excelled at understanding natural language and integrating cross-…

• Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning

  Sahil Mishra, Srinitish Srinivasan, Sourish Dasgupta, Tanmoy Chakraborty · 4 mai 2026

  Real-world knowledge is often organized as hierarchies such as product taxonomies, medical ontologies, and label trees, yet learning hierarchical representations is challenging due to asymmetric structure and noisy semantics. We introduce Polaris, a polar hyperspherical embedding framework that sepa…

• Towards Robust and Scalable Density-based Clustering via Graph Propagation

  Yingtao Zheng, Hugo Phibbs, Ninh Pham · 4 mai 2026

  We present \textit{CluProp}, a novel framework that reimagines varied-density clustering in high-dimensional spaces as a label propagation process over neighborhood graphs. Our approach formally bridges the gap between density-based clustering and graph connectivity, leveraging efficient propagation…

• Semantic Level of Detail for Knowledge Graphs: Discovering Abstraction Boundaries via Spectral Heat Diffusion

  Edward Izgorodin · 4 mai 2026

  Graph-structured knowledge systems -- from knowledge graphs to GraphRAG pipelines -- organize information into hierarchical communities, yet lack a principled mechanism for continuous resolution control: where do the qualitative boundaries between abstraction levels lie, and how should an agent navi…

• On the Expressive Power of GNNs to Solve Linear SDPs

  Chendi Qian, Christopher Morris · 1 mai 2026

  Semidefinite programs (SDPs) are a powerful framework for convex optimization and for constructing strong relaxations of hard combinatorial problems. However, solving large SDPs can be computationally expensive, motivating the use of machine learning models as fast computational surrogates. Graph ne…

• A Unified Framework of Hyperbolic Graph Representation Learning Methods

  Sof\'ia P\'erez Casulo, Marcelo Fiori, Bernardo Marenco, Federico Larroca · 1 mai 2026

  Hyperbolic geometry has emerged as an effective latent space for representing complex networks, owing to its ability to capture hierarchical organization and heterogeneous connectivity patterns using low-dimensional embeddings. As a result, numerous hyperbolic graph representation learning methods h…

• TypeBandit: Type-Level Context Allocation and Reweighting for Effective Attribute Completion in Heterogeneous Graph Neural Networks

  Ta-Yang Wang, Rajgopal Kannan, Viktor Prasanna · 1 mai 2026

  Heterogeneous graphs are widely used to model multi-relational systems, but missing node attributes remain a major bottleneck for downstream learning. In this paper, we identify and formalize type-dependent information asymmetry: the phenomenon that different node types provide substantially differe…

• Knowledge Graph Representations for LLM-Based Policy Compliance Reasoning

  Wilder Baldwin, Sepideh Ghanavati · 1 mai 2026

  The risks posed by AI features are increasing as they are rapidly integrated into software applications. In response, regulations and standards for safe and secure AI have been proposed. In this paper, we present an agentic framework that constructs knowledge graphs (KGs) from AI policy documents an…

• Robust Learning on Heterogeneous Graphs with Heterophily: A Graph Structure Learning Approach

  Yihan Zhang, Ercan E. Kuruoglu · 1 mai 2026

  Heterogeneous graphs with heterophily have emerged as a powerful abstraction for modeling complex real-world systems, where nodes of different types and labels interact in diverse and often non-homophilous ways. Despite recent advances, robust representation learning for such graphs remains largely …

• Graph World Models: Concepts, Taxonomy, and Future Directions

  Jiawei Liu, Senqiao Yang, Mingjun Wang, Yu Wang, Bei Yu · 1 mai 2026

  As one of the mainstream models of artificial intelligence, world models allow agents to learn the representation of the environment for efficient prediction and planning. However, classical world models based on flat tensors face several key problems, including noise sensitivity, error accumulation…

• Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusion

  Yonghao Liu, Jialu Sun, Wei Pang, Fausto Giunchiglia, Ximing Li, Xiaoyue Feng, Renchu Guan · 1 mai 2026

  Graph few-shot learning, which focuses on effectively learning from only a small number of labeled nodes to quickly adapt to new tasks, has garnered significant research attention. Despite recent advances in graph few-shot learning that have demonstrated promising performance, existing methods still…

• Sparse Graph Learning from Sparse Data via Fiedler Number Maximization

  Bahar Oveisgharan, Gene Cheung, Andrew Eckford · 30 avril 2026

  We aim to learn a sparse and connected graph from sparse data, where the number of observations K can be substantially smaller than the signal dimension N for signals x in R^N, and the underlying distribution is unknown. In this severely ill-posed setting, we incorporate Fiedler number (the second e…

• Incremental Strongly Connected Components with Predictions

  Ronald Deng, Samuel McCauley, Aidin Niaparast, Helia Niaparast, Bennett Ptak, Shirel Quintanilla, Shikha Singh, Nathan Vosburg · 30 avril 2026

  Algorithms with predictions is a growing area that aims to leverage machine-learned predictions to design faster beyond-worst-case algorithms. In this paper, we use this framework to design a learned data structure for the incremental strongly connected components (SCC) problem. In this problem, the…

• Graph Property Inference in Small Language Models: Effects of Representation and Reasoning Strategy

  Michal Podstawski · 30 avril 2026

  Recent progress in language modeling has expanded the range of tasks that can be approached through natural language interfaces, including problems that require structured reasoning. However, it remains unclear how effectively limited-capacity language models can infer formal properties of relationa…

• Cheeger--Hodge Contrastive Learning for Structurally Robust Graph Representation Learning

  Mengyang Zhao, Longlong Li, Cunquan Qu · 30 avril 2026

  Graph Contrastive Learning (GCL) has emerged as a prominent framework for unsupervised graph representation learning. However, relying on augmentation design alone to define the invariances learned by GCL can be brittle under structural perturbations. To address this issue, we propose Cheeger--Hodge…

• A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication

  Valentin Cuzin-Rambaud (LIRIS, UCBL), Laetitia Matignon (LIRIS, UCBL), Maxime Morge (LIRIS, UCBL) · 30 avril 2026

  In multi-agent reinforcement learning (MARL), the integration of a communication mechanism, allowing agents to better learn to coordinate their actions and converge on their objectives by sharing information. Based on an interaction graph, a subclass of methods employs graph neural networks (GNNs) t…

• Mini-Batch Class Composition Bias in Link Prediction

  Kieran Maguire, Srinandan Dasmahapatra · 30 avril 2026

  Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. For a fixed graph, one would then expect GNNs trained for link prediction to learn a representation consistent with that l…

• Enabling Transparent Cyber Threat Intelligence Combining Large Language Models and Domain Ontologies

  Luca Cotti, Anisa Rula, Devis Bianchini, Federico Cerutti · 29 avril 2026

  Effective Cyber Threat Intelligence (CTI) relies upon accurately structured and semantically enriched information extracted from cybersecurity system logs. However, current methodologies often struggle to identify and interpret malicious events reliably and transparently, particularly in cases invol…