Advanced Graph Neural Networks

Derniers papiers

• Geodesics of Dynamic Graphs for Regime Change Detection

  William Cappelletti, \'Etienne Voutaz, Pascal Frossard · 8 juin 2026

  Traditional change point detection in dynamic networks assumes abrupt transitions between stationary states, overlooking scenarios of continuous evolution which arise in most real-world applications, such as social networks or physical systems. We address this gap by formally defining regimes as per…

• Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs

  Takuto Takahashi, Itsuki Nakayama, Takahiro Mitani, Ryosuke Kikuchi, Yuya Sasaki, Makoto Onizuka · 8 juin 2026

  Node classification in graph neural networks (GNNs) has been widely applied in various fields of graph analysis. GNNs achieve high-accuracy node classification in homophilous graphs, where nodes with the same class label tend to be connected. However, their performance remains limited in heterophilo…

• ADAGE: Active Defenses Against GNN Extraction

  Jing Xu, Franziska Boenisch, Adam Dziedzic · 8 juin 2026

  Graph Neural Networks (GNNs) achieve high performance in various real-world applications, such as drug discovery, traffic states prediction, and recommendation systems. The fact that building powerful GNNs requires a large amount of training data, powerful computing resources, and human expertise tu…

• The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learning

  Shuo Wang, Xiangyu Wang, Quanxin Wang, Bailin Wu, Bokui Wang, Shunyang Huang, Boyan Deng, Haonan Liu, Ruiyi Fang, Zhenxiang Xu, Boyu Wang, Zhao Kang · 8 juin 2026

  Current evaluation practices in relational learning rely heavily on flat leaderboards that average performance across heterogeneous datasets, implicitly assuming a uniform underlying structure. We show that this assumption introduces systematic bias: it obscures geometry-dependent performance variat…

• The Geometry of Last-Layer Model Stealing

  Snigdha Chandan Khilar · 8 juin 2026

  This paper uses geometry to explain how a machine learning model can be stolen using an already existing well-known method. The author has shown the exact conditions required to perfectly copy the final layer of a transformer network. When looking deeper into the hidden layers the author has explain…

• Beyond Vector Similarity: A Structural Analysis of Graph-Augmented Retrieval for Industrial Knowledge Graphs

  Grama Chethan · 5 juin 2026

  Retrieval-Augmented Generation (RAG) fails systematically on queries requiring structural reasoning over interconnected entities. We compare eight retrieval architectures for aerospace supply chain intelligence, progressing from text retrieval through graph traversal to graph computation. Using a 46…

• GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data

  Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Kumar Gyawali, Gianfranco Doretto, Donald A. Adjeroh · 5 juin 2026

  We investigate how to make small tabular foundation models effective for High-Dimensional, Low-Sample Size (HDLSS) tabular prediction without retraining large backbones. We introduce Graph-guided Ordering with Local Refinement (GO-LR), show its equivalence to weighted Minimum Linear Arrangement, and…

• Harnessing Structural Context for Entity Alignment Foundation Models

  Xingyu Chen, Yuanning Cui, Zequn Sun, Wei Hu · 5 juin 2026

  Entity alignment (EA) aims to identify equivalent entities across heterogeneous knowledge graphs (KGs) and is a key component of knowledge fusion and cross-KG reasoning. The recent EA foundation model demonstrates that alignment knowledge, once pretrained, can be directly applied to diverse previous…

• Generating Graph-Like Logical Rules for Knowledge Graph Reasoning via Diffusion Models

  Haoxiang Cheng, Yunfei Wang, Chao Chen, Kewei Cheng, Zhipeng Lin, Haoxuan Li, Changjun Fan, Shixuan Liu · 5 juin 2026

  Logical rules constitute a cornerstone of knowledge graph (KG) reasoning, valued for their interpretability and ability to model relational patterns. However, existing rule mining methods predominantly focus on simple chain-like rules and therefore neglect the richer relational information encoded i…

• Multilingual Fine-Tuning via Localized Gradient Conflict Resolution

  Long P. Hoang, Yiran Zhao, Wei Lu, Wenxuan Zhang · 5 juin 2026

  The rapid evolution of Large Language Models (LLMs) has established cross-lingual versatility as a defining feature of modern systems. However, fine-tuning these models frequently induces negative interference across languages. To address this, we reformulate multilingual fine-tuning as a multi-obje…

• Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents

  Shuo Ji, Yibo Li, Bryan Hooi · 5 juin 2026

  Despite recent progress, LLM agents still struggle with reasoning over long interaction histories. While current memory-augmented agents rely on a static retrieve-then-reason paradigm, this rigid pipeline design prevents them from dynamically adapting memory access to intermediate evidence discovere…

• Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning

  Meher Chaitanya, My Le, Luana Ruiz · 4 juin 2026

  We introduce Graph Cascades, a mesoscopic rewiring strategy for Graph Neural Networks (GNNs) and Graph Transformers (GTs) that captures intermediate-scale graph structure beyond purely local edges or fully global attention. Using contagion-based diffusion processes, Graph Cascades constructs, in O(|…

• Bayesian Membership Privacy for Graph Neural Networks

  Sinan Y{\i}ld{\i}r{\i}m, Megha Khosla · 4 juin 2026

  Existing privacy analyses for Graph Neural Networks (GNNs) largely inherit assumptions from non-graph settings, overlooking structural correlations and stochastic training-graph sampling. In particular, node-dependent priors make type-I and type-II errors alone insufficient to characterize the best …

• Graph Set Transformer

  Jose E. Escrig Molina, Baoquan Chen, Daniel Probst · 4 juin 2026

  We introduce the Graph Set Transformer (GST), a neural network architecture for learning on sets of graphs, designed for tasks in which per-element predictions depend on set-wide context as well as local structure. Existing architectures, including DeepSets and SetTransformer, require pre-encoded gr…

• ALINC: Active Learning for Inductive Node Classification via Graph Sampling

  Pascal Plettenberg, Denis Huseljic, Andr\'e Alcalde, Bernhard Sick, Josephine M. Thomas · 4 juin 2026

  Active learning (AL) for node classification typically focuses on selecting the most informative nodes for annotation within one or a few large graphs (e.g., in social network analysis). However, in other domains, such as molecular chemistry or electronic design automation, datasets consist of thous…

• QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation

  Prerana Ramkumar, Nouhaila Innan, Muhammad Shafique · 4 juin 2026

  Scene Graph Generation (SGG) requires relational reasoning over objects and their interactions, but performance is often limited by severe long-tail predicate imbalance. Classical SGG models frequently rely on dataset statistics, leading to biased predictions toward frequent relations rather than fi…

• LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models

  Yuanrui Wang, Xingxuan Zhang, Han Yu, Mingchao Ming, Gang Ren, Hao Yuan, Li Mao, Yunjia Zhang, Chun Yuan, Peng Cui · 4 juin 2026

  Tabular foundation models (TFMs) increasingly rival tree ensembles, but their performance is often compute-inefficient: with standard affine scalar tokenization, each feature injects value variation through an essentially one-dimensional channel, and feature IDs/positional signals cannot increase wi…

• Learning Long Range Spatio-Temporal Representations over Continuous Time Dynamic Graphs with State Space Models

  Ayushman Raghuvanshi, Thummaluru Siddartha Readdy, Sundeep Prabhakar Chepuri, Mahesh Chandran · 4 juin 2026

  Continuous-time dynamic graphs (CTDGs) provide a richer framework to capture fine-grained temporal patterns in evolving relational data. Long-range information propagation is a key challenge while learning representations, wherein it is important to retain and update information over long temporal h…

• Identifying and Correcting Label Noise for Robust GNNs via Influence Contradiction

  Wei Ju, Wei Zhang, Siyu Yi, Zhengyang Mao, Yifan Wang, Jingyang Yuan, Zhiping Xiao, Ziyue Qiao, Ming Zhang · 4 juin 2026

  Graph Neural Networks (GNNs) have shown remarkable capabilities in learning from graph-structured data with various applications such as social analysis and bioinformatics. However, the presence of label noise in real scenarios poses a significant challenge in learning robust GNNs, and their effecti…

• What Structural Inductive Bias Helps Transformers Reason Over Knowledge Graphs? A Study with Tabula RASA

  Jonas Petersen, Camilla Mazzoleni, Gian-Alessandro Lombardi, Federico Martelli, Riccardo Maggioni · 4 juin 2026

  What structural inductive bias helps transformers reason over knowledge graphs? Through controlled ablations of a minimal transformer modification with four independently removable components (sparse adjacency masking, edge-type biases, query scaling, value gating), we isolate which structural signa…

• In-Context Graphical Inference

  Zehua Cheng, Wei Dai, Jiahao Sun · 4 juin 2026

  Marginal inference in discrete graphical models forces a choice between exactness and scalability: exact algorithms are intractable for high-treewidth graphs, while iterative approximations (Belief Propagation, variational methods) sacrifice convergence guarantees on frustrated topologies. We argue …

• Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs

  Weiwei Ding, Zixuan Li, Long Bai, Zhuo Chen, Kun Su, Fei Wang, Xiaolong Jin, Jin Zhang, Jiafeng Guo, Xueqi Cheng · 3 juin 2026

  Knowledge Graphs (KGs) are widely used to mitigate the limitations of Large Language Models (LLMs), such as outdated knowledge and hallucinations. Existing LLM-KG integration frameworks typically rely on predefined operators to retrieve factual knowledge from KGs and inject it into prompts for answe…

• Explainable Forecasting of Scientific Breakthroughs from Concept Network Dynamics

  Thomas Maillart, Thibaut Chataing, Ntorina Antoni, David Dosu, Paul Bagourd, Julian Jang-Jaccard, Alain Mermoud · 3 juin 2026

  We introduce an explainable machine-learning approach that forecasts the structural precursors of scientific breakthroughs -- the emergence and intensification of links between research concepts -- by modelling how OpenAlex concept networks evolve over time. Using 59 semantic and topological feature…

• Contrastive Neural Algorithmic Reasoning for Graph Coloring

  Thien Le, Tianyu Zhao, Melanie Weber · 3 juin 2026

  Graph coloring seeks to assigns colors to a graph's nodes so that adjacent nodes receive different colors, using as few colors as possible. Here, we study approximate $k$-coloring, where the goal is to use at most $k$ colors while minimizing the number of monochromatic edges. This problem is central…

• Text-attributed Graph Condensation via Text Selection and Attribute Matching

  Haowei Han, Yuxiang Wang, Guojia Wan, Hao Wang, Shanshan Feng, Hao Huang, Jiawei Jiang, Xiao Yan · 3 juin 2026

  Text-Attributed Graph (TAG) is an important type of graph structured data, where each node has a text description. TAG models usually train a Graph Neural Network (GNN) and language model jointly, which leads to high space and time consumption, especially on large datasets. To mitigate this, we prop…