Advanced Graph Neural Networks

Derniers papiers

• Dual-Kernel Graph Community Contrastive Learning

  Xiang Chen, Kun Yue, Wenjie Liu, Zhenyu Zhang, Liang Duan · 12 novembre 2025

  Graph Contrastive Learning (GCL) has emerged as a powerful paradigm for training Graph Neural Networks (GNNs) in the absence of task-specific labels. However, its scalability on large-scale graphs is hindered by the intensive message passing mechanism of GNN and the quadratic computational complexit…

• Generalizable Insights for Graph Transformers in Theory and Practice

  Timo Stoll, Luis M\"uller, Christopher Morris · 12 novembre 2025

  Graph Transformers (GTs) have shown strong empirical performance, yet current architectures vary widely in their use of attention mechanisms, positional embeddings (PEs), and expressivity. Existing expressivity results are often tied to specific design choices and lack comprehensive empirical valida…

• ARAC: Adaptive Regularized Multi-Agent Soft Actor-Critic in Graph-Structured Adversarial Games

  Ruochuan Shi, Runyu Lu, Yuanheng Zhu, Dongbin Zhao · 12 novembre 2025

  In graph-structured multi-agent reinforcement learning (MARL) adversarial tasks such as pursuit and confrontation, agents must coordinate under highly dynamic interactions, where sparse rewards hinder efficient policy learning. We propose Adaptive Regularized Multi-Agent Soft Actor-Critic (ARAC), wh…

• One Router to Route Them All: Homogeneous Expert Routing for Heterogeneous Graph Transformers

  Georgiy Shakirov, Albert Arakelov · 12 novembre 2025

  A common practice in heterogeneous graph neural networks (HGNNs) is to condition parameters on node/edge types, assuming types reflect semantic roles. However, this can cause overreliance on surface-level labels and impede cross-type knowledge transfer. We explore integrating Mixture-of-Experts (MoE…

• Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics

  Tai Hoang, Alessandro Trenta, Alessio Gravina, Niklas Freymuth, Philipp Becker, Davide Bacciu, Gerhard Neumann · 12 novembre 2025

  Learning to simulate complex physical systems from data has emerged as a promising way to overcome the limitations of traditional numerical solvers, which often require prohibitive computational costs for high-fidelity solutions. Recent Graph Neural Simulators (GNSs) accelerate simulations by learni…

• Safeguarding Graph Neural Networks against Topology Inference Attacks

  Jie Fu, Yuan Hong, Zhili Chen, Wendy Hui Wang · 12 novembre 2025

  Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, their widespread adoption has raised serious privacy concerns. While prior research has primarily focused on edge-level privacy, a critical yet underexplored threat lies in topology privacy…

• A General Method for Proving Networks Universal Approximation Property

  Wei Wang · 12 novembre 2025

  Deep learning architectures are highly diverse. To prove their universal approximation properties, existing works typically rely on model-specific proofs. Generally, they construct a dedicated mathematical formulation for each architecture (e.g., fully connected networks, CNNs, or Transformers) and …

• Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs

  Zhongyang Li, Ziyue Li, Tianyi Zhou · 11 novembre 2025

  Sparse Mixture-of-Experts (MoE) have been widely adopted in recent large language models since it can efficiently scale up the model capability without increasing the inference cost. However, evaluations on broad downstream tasks reveal a consistent suboptimality of the routers in existing MoE LLMs,…

• MCFCN: Multi-View Clustering via a Fusion-Consensus Graph Convolutional Network

  Chenping Pei, Fadi Dornaika, Jingjun Bi · 11 novembre 2025

  Existing Multi-view Clustering (MVC) methods based on subspace learning focus on consensus representation learning while neglecting the inherent topological structure of data. Despite the integration of Graph Neural Networks (GNNs) into MVC, their input graph structures remain susceptible to noise i…

• MoEGCL: Mixture of Ego-Graphs Contrastive Representation Learning for Multi-View Clustering

  Jian Zhu, Xin Zou, Jun Sun, Cheng Luo, Lei Liu, Lingfang Zeng, Ning Zhang, Bian Wu, Chang Tang, Lirong Dai · 11 novembre 2025

  In recent years, the advancement of Graph Neural Networks (GNNs) has significantly propelled progress in Multi-View Clustering (MVC). However, existing methods face the problem of coarse-grained graph fusion. Specifically, current approaches typically generate a separate graph structure for each vie…

• How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation

  Zinuo You, Jin Zheng, John Cartlidge · 11 novembre 2025

  Existing graph neural networks typically rely on heuristic choices for hidden dimensions and propagation depths, which often lead to severe information loss during propagation, known as over-squashing. To address this issue, we propose Channel Capacity Constrained Estimation (C3E), a novel framework…

• Optimizing Chain-of-Thought Confidence via Topological and Dirichlet Risk Analysis

  Abhishek More, Anthony Zhang, Nicole Bonilla, Ashvik Vivekan, Kevin Zhu, Parham Sharafoleslami, Maheep Chaudhary · 11 novembre 2025

  Chain-of-thought (CoT) prompting enables Large Language Models to solve complex problems, but deploying these models safely requires reliable confidence estimates, a capability where existing methods suffer from poor calibration and severe overconfidence on incorrect predictions. We propose Enhanced…

• Beyond Fixed Depth: Adaptive Graph Neural Networks for Node Classification Under Varying Homophily

  Asela Hevapathige, Asiri Wijesinghe, Ahad N. Zehmakan · 11 novembre 2025

  Graph Neural Networks (GNNs) have achieved significant success in addressing node classification tasks. However, the effectiveness of traditional GNNs degrades on heterophilic graphs, where connected nodes often belong to different labels or properties. While recent work has introduced mechanisms to…

• LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs

  Himanshu Pal, Venkata Sai Pranav Bachina, Ankit Gangwal, Charu Sharma · 11 novembre 2025

  Temporal Graph Neural Networks (TGNNs) are increasingly used in high-stakes domains, such as financial forecasting, recommendation systems, and fraud detection. However, their susceptibility to poisoning attacks poses a critical security risk. We introduce LoReTTA (Low Resource Two-phase Temporal At…

• Sheaf Graph Neural Networks via PAC-Bayes Spectral Optimization

  Yoonhyuk Choi, Jiho Choi, Chong-Kwon Kim · 11 novembre 2025

  Over-smoothing in Graph Neural Networks (GNNs) causes collapse in distinct node features, particularly on heterophilic graphs where adjacent nodes often have dissimilar labels. Although sheaf neural networks partially mitigate this problem, they typically rely on static or heavily parameterized shea…

• Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks

  Dian Jin, Yancheng Yuan, Xiaoming Tao · 11 novembre 2025

  Pretrained equivariant graph neural networks based on spherical harmonics offer efficient and accurate alternatives to computationally expensive ab-initio methods, yet adapting them to new tasks and chemical environments still requires fine-tuning. Conventional parameter-efficient fine-tuning (PEFT)…

• Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling

  Xin He, Yili Wang, Yiwei Dai, Xin Wang · 11 novembre 2025

  Over-smoothing remains a fundamental challenge in deep Graph Neural Networks (GNNs), where repeated message passing causes node representations to become indistinguishable. While existing solutions, such as residual connections and skip layers, alleviate this issue to some extent, they fail to expli…

• Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time

  Junjun Pan, Yixin Liu, Chuan Zhou, Fei Xiong, Alan Wee-Chung Liew, Shirui Pan · 11 novembre 2025

  Graph anomaly detection (GAD), which aims to detect outliers in graph-structured data, has received increasing research attention recently. However, existing GAD methods assume identical training and testing distributions, which is rarely valid in practice. In real-world scenarios, unseen but normal…

• On Stealing Graph Neural Network Models

  Marcin Podhajski, Jan Dubi\'nski, Franziska Boenisch, Adam Dziedzic, Agnieszka Pr\k{e}gowska, Tomasz P. Michalak · 11 novembre 2025

  Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed queries can be severely limited. In this paper, we demonstrate how an adversary can extract the GNN with very limited inter…

• Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees

  Mohammad Shirzadi, Ali Safarpoor Dehkordi, Ahad N. Zehmakan · 11 novembre 2025

  Message passing is the core operation in graph neural networks, where each node updates its embeddings by aggregating information from its neighbors. However, in deep architectures, this process often leads to diminished expressiveness. A popular solution is to use residual connections, where the in…

• Breaking the Dyadic Barrier: Rethinking Fairness in Link Prediction Beyond Demographic Parity

  Jo\~ao Mattos, Debolina Halder Lina, Arlei Silva · 11 novembre 2025

  Link prediction is a fundamental task in graph machine learning with applications, ranging from social recommendation to knowledge graph completion. Fairness in this setting is critical, as biased predictions can exacerbate societal inequalities. Prior work adopts a dyadic definition of fairness, en…

• Learning Time-Varying Graph Signals via Koopman

  Sivaram Krishnan, Jinho Choi, Jihong Park · 11 novembre 2025

  A wide variety of real-world data, such as sea measurements, e.g., temperatures collected by distributed sensors and multiple unmanned aerial vehicles (UAV) trajectories, can be naturally represented as graphs, often exhibiting non-Euclidean structures. These graph representations may evolve over ti…

• A Graph Laplacian Eigenvector-based Pre-training Method for Graph Neural Networks

  Howard Dai, Nyambura Njenga, Hiren Madhu, Siddharth Viswanath, Ryan Pellico, Ian Adelstein, Smita Krishnaswamy · 11 novembre 2025

  The development of self-supervised graph pre-training methods is a crucial ingredient in recent efforts to design robust graph foundation models (GFMs). Structure-based pre-training methods are under-explored yet crucial for downstream applications which rely on underlying graph structure. In additi…

• Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networks

  Yanan Zhao, Feng Ji, Jingyang Dai, Jiaze Ma, Keyue Jiang, Kai Zhao, Wee Peng Tay · 11 novembre 2025

  Graph contrastive learning (GCL) learns node and graph representations by contrasting multiple views of the same graph. Existing methods typically rely on fixed, handcrafted views-usually a local and a global perspective, which limits their ability to capture multi-scale structural patterns. We pres…

• DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains

  Yongkang Xiao, Sinian Zhang, Yi Dai, Huixue Zhou, Jue Hou, Jie Ding, Rui Zhang · 11 novembre 2025

  Knowledge graph completion (KGC) aims to predict missing triples in knowledge graphs (KGs) by leveraging existing triples and textual information. Recently, generative large language models (LLMs) have been increasingly employed for graph tasks. However, current approaches typically encode graph con…