Advanced Graph Neural Networks

Derniers papiers

• Spectral Flow Certificates for Depth-Aware Long-Range Propagation in Graph Neural Networks

  Ranjan Veerabhadraswamy, Ajith Jubilson Emerson · 27 juillet 2026

  Graph Neural Networks propagate information through local message passing, but the graph topologies themselves can silently prevent any amount of training from solving long-range tasks. When we deploy GNNs on new graphs, there is currently no inexpensive way to know, before training begins, whether …

• Towards Trustworthy and Cost-Efficient Data Integration: From Na\"ive RAG to Agentic RAG

  Chuangtao Ma, Arijit Khan · 27 juillet 2026

  Large language models (LLMs) and AI agents have demonstrated strong potential for data integration in zero-shot and few-shot settings. However, they continue to face significant accuracy and cost challenges in enterprise environments due to a persistent knowledge gap. This paper envisions trustworth…

• MotifRole-Diff: Risk-Optimal Role-Aware Corruption for Masked Molecular Graph Diffusion

  Tasfia Nuzhat Ornee, Elias Hossain, Ivan Garibay, Niloofar Yousef · 27 juillet 2026

  Masked discrete diffusion for molecular graph generation typically applies a uniform corruption schedule to all tokens in a lossless graph-to-sequence representation, implicitly treating structurally heterogeneous molecular components as equally difficult and equally important to reconstruct. Howeve…

• Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature

  Rachid Caich, Yassine Abbahaddou · 27 juillet 2026

  Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Networks (GNNs) such as oversmoothing and oversquashing, but rely almost exclusively on local edge-level comparisons and therefore fail to certify how…

• MA-DAR: Manifold-Aligned Dynamic Adaptive Routing for Continual Temporal Knowledge Graph Reasoning

  Xiangjun Shi, Chong Mu, Jinchuan Zhang, Lizong Zhang, Yuefeng He, Shang Liu · 27 juillet 2026

  Continual temporal knowledge graph (TKG) reasoning aims to continuously incorporate newly emerging facts while preserving previously acquired knowledge. Replay-based continual learning has achieved promising performance by revisiting historical representations. However, existing methods primarily fo…

• Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement

  Guoming Li, Jian Yang, Xukun Wang, Zixiao Wang, Shangsong Liang, Yifan Chen · 27 juillet 2026

  Coarsening-based training for graph neural networks (GNNs), i.e.\ training on coarsened graphs rather than the original large ones, has become a promising direction for scaling GNNs to massive graphs. However, prior work has been evaluated almost exclusively on \textit{homophilic} graphs, leaving th…

• FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding

  Theodoros Aivalis, Iraklis A. Klampanos, Antonis Troumpoukis, Joemon M. Jose · 27 juillet 2026

  The rapid deployment of generative AI has amplified the critical need for Training Data Attribution to ensure transparency and accountability. However, current parametric approaches require computationally prohibitive access to model weights, while similarity-based methods ignore deep structural con…

• Efficient Recommendations via Graph Coarsening and Label Propagation

  Alessandro Sbandi, Federico Siciliano, Fabrizio Silvestri · 27 juillet 2026

  Graph-based recommendations are widely adopted in real-world industrial applications. However, graphs in these systems often reach a massive scale, posing notable scalability and efficiency challenges. This requires techniques that can effectively balance predictive quality with computational cost. …

• Optimizing Hypergraph-Based RAG: Toward Better Fact Extraction and Chunk Retrieval

  Houda Khrouf, Pedro Fillastre, Sebastiao Correia · 24 juillet 2026

  GraphRAG enables deeper reasoning by structuring knowledge as graphs but struggles with n-ary facts. HyperGraphRAG uses hypergraphs for richer semantics, improving accuracy, yet relies on error-prone LLM extraction and inefficient standard chunk retrieval. We address this by employing self-consisten…

• Routing Without Training: Controllable-Ratio LLM Offloading via Reliability Gating

  Evan Chen, Shiqiang Wang, Kevin S Chan, Su Wang, Christopher Brinton · 24 juillet 2026

  Local-cloud collaboration is a practical way to deploy large language models under resource constraints, but existing methods often rely on trained routers or collaboration-aware finetuning that tie routing behavior to a particular operating regime. In this work, we show that such training may be un…

• AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphs

  Fanjin Zhang, Zhengyang Wang, Ruixuan Huang, Kefan Zhang, Amy Xin, Yuanchun Wang, Shu Zhao, Evgeny Kharlamov, Jie Tang, Juanzi Li · 24 juillet 2026

  Large language models (LLMs) augmented with tools are emerging as autonomous agents capable of using Web engine, APIs, and code to solve complex, long-horizon tasks. Current tool-using benchmarks for information seeking on academic graphs rely on synthetic templates, simplified solution spaces, or n…

• Representing Entity Importance in AI Knowledge Systems: A Dual-Signal Framework of Audience Evaluation and Structural Authority

  Shen Xu · 24 juillet 2026

  AI knowledge systems require representations of entity importance for retrieval, recommendation, evidence selection, and knowledge-intensive reasoning. Yet importance is often reduced to a single score derived from either human response or graph structure. Such compression may discard distinctions t…

• Cardinality-Decomposed Loss: Matching Training Objectives to Relation Structure in Heterogeneous Recommendation Graphs

  Parul Maheshwari, Amulya Paruchuri, Yiqing Zou, Alireza Sahami Shirazi, Farhad Farahani, Prakhar Mehrotra · 24 juillet 2026

  Graph Neural Networks trained on heterogenous bipartite graphs form a common basis in recommendation systems. These graphs often express relations that vary in cardinality, for example, user-item preferences are one-to-many and user-attribute features are one-to-one. Traditionally, a unique loss fun…

• Filter Learning for Subgraphs: Algebras and Performance Risk Bounds

  Purui Zhang, Feng Ji, Yanan Zhao, Bihan Wen, Wee Peng Tay · 24 juillet 2026

  Graph signal processing tasks that leverage spectral information typically assume access to the complete graph topology, which is often unavailable in practice. We propose a systematic framework for subgraph filter learning (SFL), where subgraph-supported operators approximate ambient graph filters …

• Semi-Supervised Text-Attributed Graph Distillation

  Yurui Lai, Samir Moustafa, Renchi Yang, Tsz Nam Chan · 24 juillet 2026

  {\em Text-Attributed Graphs} (TAGs) have emerged as an expressive data model for integrating graph topology with rich textual semantics. Existing representation learning methods over TAGs suffer from severe scalability bottlenecks, particularly together with {\em Large Language Models} (LLMs). While…

• A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs

  Bizu Feng, Zhimu Yang, Shuming Wang, Shaode Yu, Yuan Cheng, Xiaojun Qian, Zixin Hu · 24 juillet 2026

  We study feature-level and node-level explanations for graph neural networks (GNNs) through the lens of Aumann-Shapley attribution. Path-integral methods such as Integrated Gradients provide an axiomatic formulation of attribution, but their practical use in deep GNNs typically relies on finite-samp…

• The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path

  Yiheng Tao, Kaiwen Cheng, Yao Lu, Chang Liu, Jie Chen · 24 juillet 2026

  Large Language Models (LLMs) are fundamentally limited by representation collapse, a bottleneck that severely degrades long-context performance. We identify that existing approaches risk drifting into one of two pathological extremes: homogenization collapse (e.g., attention sinks causing rank defic…

• Bridging the Gap Between Plausibility and Admissibility: Constraint-Aware Flow Maps for Dynamic Graph Systems

  Michael Romei de Socio, Gian Luca Pozzato, Alessio Merlo · 24 juillet 2026

  Generative models can support decision-making under uncertainty by producing ensembles of plausible future system trajectories, but statistical plausibility does not ensure structural feasibility. This study investigates whether post-sampling symbolic constraints can improve the reliability of gener…

• The Mechanism Matters: When Knowledge Graphs Help Reinforcement Learning

  Mohammed Sameer Syed · 23 juillet 2026

  Knowledge graphs (KGs) are widely used to inject prior knowledge into reinforcement learning (RL), yet the literature is dominated by single-domain, positive-result method papers, so we lack a systematic account of when KG structure helps an agent, when it is neutral, and when it hurts. We conduct a…

• FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense

  Chenyu Zhou, Yabin Peng, Wei Huang, Kunlin Li, Shuaishuai Zhang, Xinyuan Miao · 23 juillet 2026

  Federated Graph Neural Networks (FedGNNs) are highly vulnerable to backdoor poisoning, yet existing defenses typically rely on rule-based approaches that lack semantic understanding, making them vulnerable to stealthy triggers and harmful to benign structures. To solve this, we present FedLSG, the f…

• Tensor Network Machine Learning for Wildfire Susceptibility Mapping: from Grokking Dynamics to Quantum Mixedness of Class Representations

  Domenico Pomarico, Alessandra Costantino, Gabriel Ramirez Sanchez, Loredana Bellantuono, Davide D' Al\`o, Mario Elia, Alessandro Fania, Francesco Giordano, Niloofar Kheirkhahan, Raffaele Lafortezza, Ester Pantaleo, Sabina Tangaro, Roberto Bellotti, Alfonso Monaco, Nicola Amoroso · 23 juillet 2026

  A quantum-inspired tensor network framework for wildfire susceptibility classification in the Gargano region is introduced, leveraging AlphaEarth embeddings and Matrix Product State models. The approach combines scalable geospatial representations with an interpretable quantum mask, enabling both bi…

• OpenRTAG: A Comprehensive Benchmark for Robust Text-Attributed Graph Learning under Data Quality Degradation

  Yuze Dai, Zhihan Zhang, Yan Zhao, Ruoyu Wu, Xunkai Li, Zekai Chen, Qiangqiang Dai, Hongchao Qin, Ronghua Li · 22 juillet 2026

  Text-attributed graphs (TAGs) are an important graph data form that combine relational structure with rich node text. However, real-world TAGs are often imperfect, with quality issues arising from text, structure, and labels, and typically manifesting as sparsity, noise, and imbalance. These dimensi…

• Finite-Agent Stochastic Differential Games on Large Graphs: II. Graph-Based Architectures

  Ruimeng Hu, Jihao Long, Haosheng Zhou · 22 juillet 2026

  We propose a novel neural network architecture, called Non-Trainable Modification (NTM), for computing Nash equilibria in stochastic differential games (SDGs) on graphs. These games model a broad class of graph-structured multi-agent systems arising in finance, robotics, energy, and social dynamics,…

• Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability

  Taewoon Kim, Vincent Fran\c{c}ois-Lavet, Michael Cochez · 22 juillet 2026

  Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time. We introduce a neuro-symbolic meta-policy that learns which symbolic memory heuristic to apply at each decision point while keeping execution symbolic. Our setting uses temporal knowledge-gr…

• Cost Accounting for Reactive Computational Graphs: Exhaustive Sweeps, Sequential Mutation, and the Backward-Locality Gap

  Abdallah Khemais (ISITCOM, University of Sousse) · 22 juillet 2026

  Exhaustive site-by-site interventions on a neural network's computational graph -- activation-patching sweeps, circuit-discovery searches, systematic ablation studies -- mutate the graph at every candidate site, and their cost is dominated by recomputation after each mutation. On a reactive graph en…