Advanced Graph Neural Networks

Derniers papiers

• Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph

  Ning Liu, Chuanneng Sun, Kristina Klinkner, Shervin Malmasi · 11 mai 2026

  Direct Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from human feedback. However, in many practical settings, training data consists of multiple rollouts per prompt, inducing ric…

• GraphReAct: Reasoning and Acting for Multi-step Graph Inference

  Xingtong Yu, Zhongwei Kuai, Chang Zhou, Xuanting Xie, Renhe Jiang, Xikun Zhang, Hong Cheng, Xinming Zhang, Yuan Fang · 11 mai 2026

  Reasoning-acting frameworks enhance large language models (LLMs) by interleaving reasoning with actions for dynamic information acquisition. However, extending this paradigm to graph learning remains underexplored. Graph data is inherently structured, with information distributed across nodes and ed…

• Have Graph -- Will Lift? The Case for Higher-Order Benchmarks

  Bastian Rieck · 11 mai 2026

  After a somewhat rocky start, geometry and topology have established a foothold in machine learning. Message passing, either on graphs or higher-order complexes, is one of the main drivers of geometric deep learning, and paradigms that were once considered to be firmly in the realm of the abstract-l…

• GRAPHLCP: Structure-Aware Localized Conformal Prediction on Graphs

  Peyman Baghershahi, Fangxin Wang, Debmalya Mandal, Sourav Medya · 11 mai 2026

  Conformal prediction (CP) provides a distribution-free approach to uncertainty quantification with finite-sample guarantees. However, applying CP to graph neural networks (GNNs) remains challenging as the combinatorial nature of graphs often leads to insufficiently certain predictions and indiscrimi…

• GAD in the Wild: Benchmarking Graph Anomaly Detection under Realistic Deployment Challenges

  Jingjing Zhou, Shiyu Huang, Qing Qing, Zuquan Yuan, Huafei Huang, Ziqi Xu, Mingliang Hou, Xikun Zhang, Renqiang Luo, Ivan Lee · 11 mai 2026

  Graph Anomaly Detection (GAD) is a critical task in graph machine learning with vital applications in financial fraud detection and social platform governance. However, existing GAD benchmarks are often restricted to small-scale, curated graphs with relatively balanced anomaly ratios, leaving a subs…

• ASPECT: Node-Level Adaptive Spectral Fusion for Graph Contrastive Learning

  Zhuolong Li, Boxue Yang, Haopeng Chen · 11 mai 2026

  Spectral graph contrastive learning often constructs low- and high-frequency views to capture complementary graph signals, but these views are commonly combined by graph-level or node-agnostic fusion rules. We show that graph-level fusion can incur irreducible regret on mixed graphs with separated n…

• DCGL: Dual-Channel Graph Learning with Large Language Models for Knowledge-Aware Recommendation

  Xinchi Zou, Tongzhenzhi Su, Jianjun Li, Yuan Fu, Chang Liu, Zhiying Deng, Zhiwei Shen · 11 mai 2026

  Knowledge Graphs (KGs) have proven highly effective for recommendation systems by capturing latent item relationships, while recent integration of Large Language Models (LLMs) has further enhanced semantic understanding and addressed knowledge sparsity issues. Nevertheless, current KG-and-LLM-based …

• Target-Aware Data Augmentation for SAT Prediction

  Eshed Gal, Uri Ascher, Eldad Haber · 11 mai 2026

  Learning-based approaches to NP-hard problems have shown increasing promise, but their progress is fundamentally constrained by the high cost of generating labeled training data. In domains such as Boolean satisfiability (SAT), standard pipelines rely on solver-in-the-loop labeling, which scales poo…

• Bilevel Graph Structure Learning, Revisited: Inner-Channel Origins of the Reported Gain

  Minkyoung Kim, Beakcheol Jang · 11 mai 2026

  Bilevel graph structure learning is widely understood to improve graph neural networks by jointly optimizing model parameters and a learned graph structure, with the resulting performance gain attributed to the rewired adjacency. We find that this attribution may be overstated: training-dynamics eff…

• Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback

  Seohyun Lee, Wenzhi Fang, Dong-Jun Han, Seyyedali Hosseinalipour, Christopher G. Brinton · 11 mai 2026

  Recent works have advanced feedback-based learning systems, whereby a foundation model is able to intake incoming feedback (e.g., a user) to self-improve, creating a self-loop system of training. However, existing works are limited in needing to consider an offline setup to allow for such feedback-b…

• RelAgent: LLM Agents as Data Scientists for Relational Learning

  Xingyue Huang, Louis Tichelman, Jinwoo Kim, Krzysztof Olejniczak, \.Ismail \.Ilkan Ceylan · 11 mai 2026

  Relational learning is a challenging problem that has motivated a wide range of approaches, including graph-based models (e.g., graph neural networks, graph transformers), tabular methods (e.g., tabular foundation models), and sequence-based approaches (e.g., large language models), each with its ow…

• Unlocking High-Fidelity Molecular Generation from Mass Spectra via Dual-Stream Line Graph Diffusion

  Xujun Che, Xiuxia Du, Depeng Xu · 11 mai 2026

  De novo molecular generation from tandem mass spectra is a challenging inverse problem whose core difficulty lies in the circular dependency between atom-level and bond-level reasoning: determining a bond's type requires knowing its endpoint atoms' chemical environment, yet an atom's environment is …

• AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning

  Seunghan Lee, Jun Seo, Jaehoon Lee, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, SoonYoung Lee, Wonbin Ahn · 11 mai 2026

  Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, existing methods produce entity representations that are static at the entity level, in that each representation is a function of learned parameters onl…

• From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning

  Debolina Halder Lina, Arlei Silva · 11 mai 2026

  Graph Neural Networks (GNNs) achieve high performance but can be opaque to humans, making it difficult to understand and compare the many proposed architectures. While existing explainability methods attribute individual predictions to nodes, edges, or features, they do not provide architectural tra…

• GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning

  Wenjin Li, Jiaming Cui · 11 mai 2026

  Large Language Models (LLMs) have demonstrated strong potential for many mathematical problems. However, their performance on graph algorithmic tasks is still unsatisfying, since graphs are naturally more complex in topology and often require systematic multi-step reasoning, especially on larger gra…

• Layout-Aware Representation Learning for Open-Set ID Fraud Discovery

  Jinxing Li, Nicholas Ren, Cathy Chang, Hongkai Pan, Daniel George · 8 mai 2026

  Identity-document fraud detection is not a stationary binary classification problem. Adaptive attackers modify templates and fabrication pipelines, making historical fraud labels stale, and successful forgeries recur at scale as coherent campaigns. We therefore study layout-aware representation lear…

• Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation

  Tran Gia Bao Ngo, Zulfikar Alom, Federico Errica, Murat Kantarcioglu, Cuneyt Gurcan Akcora · 8 mai 2026

  Adversarial learning and the robustness of Graph Neural Networks (GNNs) are topics of widespread interest in the machine learning community, as documented by the number of adversarial attacks and defenses designed for these purposes. While a rigorous evaluation of these adversarial methods is necess…

• Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Models

  Kossi Amouzouvi, Robert Wardenga, Jens Lehmann, Sahar Vahdati · 8 mai 2026

  Foundation models excel at language, where sentences become tokens, and vision, where images become pixels, because both reduce to discrete symbols on a shared, fixed grid. Knowledge Graphs share the discreteness, but not the geometry. Their entities and relations are discrete symbols, yet their arr…

• Geometry-Aware Simplicial Message Passing

  Elena Xinyi Wang, Bastian Rieck · 8 mai 2026

  The Weisfeiler--Lehman (WL) test and its simplicial extension (SWL) characterize the combinatorial expressivity of message passing networks, but they are blind to geometry, i.e., meshes with identical connectivity but different embeddings are indistinguishable. We introduce the Geometric Simplicial …

• A Unified Benchmark for Evaluating Knowledge Graph Construction Methods and Graph Neural Networks

  Othmane Kabal, Mounira Harzallah, Fabrice Guillet, Hideaki Takeda, Ryutaro Ichise · 8 mai 2026

  Knowledge graphs automatically constructed from text are increasingly used in real-world applications. However, their inherent noise, fragmentation, and semantic inconsistencies significantly affect the performance of Graph Neural Networks (GNNs) on downstream tasks. Assessing their performance and …

• On the Safety of Graph Representation Learning

  Xiaoguang Guo, Zehong Wang, Ziming Li, Shawn Spitzel, Soonwoo Kwon, Tianyi Ma, Yanfang Ye, Chuxu Zhang · 8 mai 2026

  Graph representation learning (GRL) has evolved from topology-only graph embeddings to task-specific supervised GNNs, and more recently to reusable representations and graph foundation models (GFMs). However, existing evaluations mainly measure clean transfer, adaptation, and task coverage. It remai…

• DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation

  Yingxu Wang, Xinwang Liu, Mengzhu Wang, Siyang Gao, Nan Yin · 8 mai 2026

  Graph Domain Adaptation (GDA) aims to transfer graph classifiers across domains with both semantic and topological shifts. Existing Euclidean adversarial methods face two challenges: Structural Degeneration, where domain confusion entangles and suppresses label-relevant topology, and Optimization In…

• Disentangled Generative Graph Representation Learning

  Xinyue Hu, Zhibin Duan, Xinyang Liu, Yuxin Li, Bo Chen, Chaojie Wang, Yilin He, Hongwei Liu, Mingyuan Zhou · 8 mai 2026

  Recently, generative graph models have shown promising results in learning graph representations through self-supervised methods. However, most existing generative graph representation learning (GRL) approaches rely on random masking across the entire graph, which overlooks the entanglement of learn…

• Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs

  Othmane Kabal, Mounira Harzallah, Fabrice Guillet, Hideaki Takeda, Ryutaro Ichise · 8 mai 2026

  Graph Self-Supervised Learning (GSSL) offers a powerful paradigm for learning graph representations without labeled data. However, existing work assumes clean, manually curated graphs. Recent advances in NLP enable the large-scale automatic extraction of knowledge graphs from text, opening new oppor…

• Invariant-Based Diagnostics for Graph Benchmarks

  Richard von Moos, Mathieu Alain, Bastian Rieck · 8 mai 2026

  Progress on graph foundation models is hindered by benchmark practices that conflate the contributions of node features and graph structure, making it hard to tell whether a model actually learns from connectivity, or whether it even needs to. We propose addressing this using graph invariants, i.e.,…