Advanced Graph Neural Networks

Derniers papiers

• Amortizing Maximum Inner Product Search with Learned Support Functions

  Theo X. Olausson, Jo\~ao Monteiro, Michal Klein, Marco Cuturi · 10 mars 2026

  Maximum inner product search (MIPS) is a crucial subroutine in machine learning, requiring the identification of key vectors that align best with a given query. We propose amortized MIPS: a learning-based approach that trains neural networks to directly predict MIPS solutions, amortizing the computa…

• Mitigating Homophily Disparity in Graph Anomaly Detection: A Scalable and Adaptive Approach

  Yunhui Liu, Qizhuo Xie, Yinfeng Chen, Xudong Jin, Tao Zheng, Bin Chong, Tieke He · 10 mars 2026

  Graph anomaly detection (GAD) aims to identify nodes that deviate from normal patterns in structure or features. While recent GNN-based approaches have advanced this task, they struggle with two major challenges: 1) homophily disparity, where nodes exhibit varying homophily at both class and node le…

• Towards Effective and Efficient Graph Alignment without Supervision

  Songyang Chen, Youfang Lin, Yu Liu, Shuai Zheng, Lei Zou · 10 mars 2026

  Unsupervised graph alignment aims to find the node correspondence across different graphs without any anchor node pairs. Despite the recent efforts utilizing deep learning-based techniques, such as the embedding and optimal transport (OT)-based approaches, we observe their limitations in terms of mo…

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

  Michal Podstawski · 10 mars 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…

• GraphProp: Training the Graph Foundation Models using Graph Properties

  Ziheng Sun, Qi Feng, Lehao Lin, Chris Ding, Jicong Fan · 10 mars 2026

  This work focuses on training graph foundation models (GFMs) that have strong generalization ability in graph-level tasks such as graph classification. Effective GFM training requires capturing information consistent across different domains. We discover that graph structures provide more consistent…

• Robustness Verification of Graph Neural Networks Via Lightweight Satisfiability Testing

  Chia-Hsuan Lu, Tony Tan, Michael Benedikt · 10 mars 2026

  Graph neural networks (GNNs) are the predominant architecture for learning over graphs. As with any machine learning model, an important issue is the detection of attacks, where an adversary can change the output with a small perturbation of the input. Techniques for solving the adversarial robustne…

• Not All Neighbors Matter: Understanding the Impact of Graph Sparsification on GNN Pipelines

  Yuhang Song, Naima Abrar Shami, Romaric Duvignau, Vasiliki Kalavri · 10 mars 2026

  As graphs scale to billions of nodes and edges, graph Machine Learning workloads are constrained by the cost of multi-hop traversals over exponentially growing neighborhoods. While various system-level and algorithmic optimizations have been proposed to accelerate Graph Neural Network (GNN) pipeline…

• The Role of Feature Interactions in Graph-based Tabular Deep Learning

  Elias Dubbeldam, Reza Mohammadi, Marit Schoonhoven, S. Ilker Birbil · 10 mars 2026

  Accurate predictions on tabular data rely on capturing complex, dataset-specific feature interactions. Attention-based methods and graph neural networks, referred to as graph-based tabular deep learning (GTDL), aim to improve predictions by modeling these interactions as a graph. In this work, we an…

• Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases

  Jun Yin, Peng Huo, Bangguo Zhu, Hao Yan, Senzhang Wang, Shirui Pan, Chengqi Zhang · 10 mars 2026

  In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to structure the RDB as a heterogeneous entity graph and adopt the graph neural network (GNN) as the predictive model. However, existing RDL methods neglect t…

• GraphSkill: Documentation-Guided Hierarchical Retrieval-Augmented Coding for Complex Graph Reasoning

  Fali Wang, Chenglin Weng, Xianren Zhang, Siyuan Hong, Hui Liu, Suhang Wang · 10 mars 2026

  The growing demand for automated graph algorithm reasoning has attracted increasing attention in the large language model (LLM) community. Recent LLM-based graph reasoning methods typically decouple task descriptions from graph data, generate executable code augmented by retrieval from technical doc…

• Hide and Find: A Distributed Adversarial Attack on Federated Graph Learning

  Jinshan Liu, Ken Li, Jiazhe Wei, Bin Shi, Bo Dong · 10 mars 2026

  Federated Graph Learning (FedGL) is vulnerable to malicious attacks, yet developing a truly effective and stealthy attack method remains a significant challenge. Existing attack methods suffer from low attack success rates, high computational costs, and are easily identified and smoothed by defense …

• Gauge Freedom and Metric Dependence in Neural Representation Spaces

  Jericho Cain · 10 mars 2026

  Neural network representations are often analyzed as vectors in a fixed Euclidean space. However, their coordinates are not uniquely defined. If a hidden representation is transformed by an invertible linear map, the network function can be preserved by applying the inverse transformation to downstr…

• Leakage Safe Graph Features for Interpretable Fraud Detection in Temporal Transaction Networks

  Hamideh Khaleghpour, Brett McKinney · 10 mars 2026

  Illicit transaction detection is often driven by transaction level attributes however, fraudulent behavior may also manifest through network structure such as central hubs, high flow intermediaries, and coordinated neighborhoods. This paper presents a time respecting, leakage safe (causal) graph fea…

• SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning

  Yuxiang Zhang, Enyan Dai · 10 mars 2026

  Graph Neural Networks (GNNs) have demonstrated remarkable success across diverse tasks. However, their generalization capability is often hindered by spurious correlations between node features and labels in the graph. Our analysis reveals that GNNs tend to exploit imperceptible statistical correlat…

• Semantics-Aware Caching for Concept Learning

  Louis Mozart Kamdem Teyou, Caglar Demir, Axel-Cyrille Ngonga Ngomo · 9 mars 2026

  Concept learning is a form of supervised machine learning that operates on knowledge bases in description logics. State-of-the-art concept learners often rely on an iterative search through a countably infinite concept space. In each iteration, they retrieve instances of candidate solutions to selec…

• MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing

  Yang Liu, Jinxuan Cai, Yishen Li, Qi Meng, Zedi Liu, Xin Li, Chen Qian, Chuan Shi, Cheng Yang · 9 mars 2026

  Large language model-based (LLM-based) multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration. MAS workflows can be naturally modeled as directed computation graphs, where nodes execute agents/sub-workflows and edges encode depende…

• On Multi-Step Theorem Prediction via Non-Parametric Structural Priors

  Junbo Zhao, Ting Zhang, Can Li, Wei He, Jingdong Wang, Hua Huang · 6 mars 2026

  Multi-step theorem prediction is a central challenge in automated reasoning. Existing neural-symbolic approaches rely heavily on supervised parametric models, which exhibit limited generalization to evolving theorem libraries. In this work, we explore training-free theorem prediction through the len…

• EchoGuard: An Agentic Framework with Knowledge-Graph Memory for Detecting Manipulative Communication in Longitudinal Dialogue

  Ratna Kandala, Niva Manchanda, Akshata Kishore Moharir, Ananth Kandala · 6 mars 2026

  Manipulative communication, such as gaslighting, guilt-tripping, and emotional coercion, is often difficult for individuals to recognize. Existing agentic AI systems lack the structured, longitudinal memory to track these subtle, context-dependent tactics, often failing due to limited context window…

• TSEmbed: Unlocking Task Scaling in Universal Multimodal Embeddings

  Yebo Wu, Feng Liu, Ziwei Xie, Zhiyuan Liu, Changwang Zhang, Jun Wang, Li Li · 6 mars 2026

  Despite the exceptional reasoning capabilities of Multimodal Large Language Models (MLLMs), their adaptation into universal embedding models is significantly impeded by task conflict. To address this, we propose TSEmbed, a universal multimodal embedding framework that synergizes Mixture-of-Experts (…

• Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks

  Yuxiang Zhang, Bin Ma, Enyan Dai · 6 mars 2026

  Graph Neural Networks (GNNs) have achieved remarkable results in various tasks. Recent studies reveal that graph backdoor attacks can poison the GNN model to predict test nodes with triggers attached as the target class. However, apart from injecting triggers to training nodes, these graph backdoor …

• Recurrent Graph Neural Networks and Arithmetic Circuits

  Timon Barlag, Vivian Holzapfel, Laura Strieker, Jonni Virtema, Heribert Vollmer · 6 mars 2026

  We characterise the computational power of recurrent graph neural networks (GNNs) in terms of arithmetic circuits over the real numbers. Our networks are not restricted to aggregate-combine GNNs or other particular types. Generalizing similar notions from the literature, we introduce the model of re…

• An LLM-Guided Query-Aware Inference System for GNN Models on Large Knowledge Graphs

  Waleed Afandi, Hussein Abdallah, Ashraf Aboulnaga, Essam Mansour · 6 mars 2026

  Efficient inference for graph neural networks (GNNs) on large knowledge graphs (KGs) is essential for many real-world applications. GNN inference queries are computationally expensive and vary in complexity, as each involves a different number of target nodes linked to subgraphs of diverse densities…

• Beyond Prefixes: Graph-as-Memory Cross-Attention for Knowledge Graph Completion with Large Language Models

  Ruitong Liu, Boxu Lin, Peize Li, Siyuan Li, Yunjia Wu, Te Sun, Chaohan Wu · 6 mars 2026

  Fusing Knowledge Graphs with Large Language Models (LLMs) is crucial for knowledge-intensive tasks like knowledge graph completion. Existing LLM-based approaches typically inject graph information via prefix concatenation, resulting in shallow interactions that fail to support fine-grained evidence …

• On the Necessity of Learnable Sheaf Laplacians

  Ferran Hernandez Caralt, Mar Gonz\`alez i Catal\`a, Adri\'an Bazaga, Pietro Li\`o · 6 mars 2026

  Sheaf Neural Networks (SNNs) were introduced as an extension of Graph Convolutional Networks to address oversmoothing on heterophilous graphs by attaching a sheaf to the input graph and replacing the adjacency-based operator with a sheaf Laplacian defined by (learnable) restriction maps. Prior work …

• Graph Hopfield Networks: Energy-Based Node Classification with Associative Memory

  Abinav Rao, Alex Wa, Rishi Athavale · 5 mars 2026

  We introduce Graph Hopfield Networks, whose energy function couples associative memory retrieval with graph Laplacian smoothing for node classification. Gradient descent on this joint energy yields an iterative update interleaving Hopfield retrieval with Laplacian propagation. Memory retrieval provi…