Advanced Graph Neural Networks

Derniers papiers

• Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph

  Peiji Yu, Xin Chen, Tianxing Wu · 21 juillet 2026

  Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing. However, LLMs often suffer from hallucinations and lack of relevant knowledge when dealing with question answering (QA) tasks. To mitigate these issues, knowledge graphs (KGs) have been utilized to…

• The Value of Depth in Message Passing on Sparse Graphs: A Kesten-Stigum Dichotomy

  Aseem Raj Baranwal · 21 juillet 2026

  How deep does a graph neural network need to be on a sparse graph? We study its purest statistical form: node classification on the sparse contextual stochastic block model (CSBM) with average degree $\Delta=O(1)$, whose local weak limit is a broadcast-labelled Poisson Galton-Watson tree. Prior work…

• TopoTuner: Topological Finetuning of Large Language Models

  Abdulkadir Erol, Yash Mahajan, Vepaul Hariprashad, Baha Rababah, Santu Karmaker, Cuneyt G. Akcora, Mubarak Shah · 21 juillet 2026

  Full fine-tuning remains a strong way to adapt pretrained LLMs, but it updates all weights and can be expensive. LoRA reduces the number of trainable parameters, but it does not directly answer which pretrained components should be trained and which can be frozen during adaptation. We introduce Topo…

• GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models

  Jiarui Feng, Donghong Cai, Yixin Chen, Muhan Zhang · 21 juillet 2026

  Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks. However, effectively adapting LLMs to structural data, such as knowledge graphs or web graphs, remains a fundamental challenge. Some approaches adopt comp…

• Selectivity Matters: Source Node Influence Pruning for Unsupervised Graph Domain Adaptation

  Ridong Han, Yawen Shen, Zhongnian Li, Tongfeng Sun, Xinzheng Xu, Abdulmotaleb El Saddik · 21 juillet 2026

  Unsupervised Graph Domain Adaptation (UGDA) aims to facilitate knowledge transfer from a labeled source graph to an unlabeled target graph by mitigating cross-domain distribution shifts. Existing methods primarily focus on node-level feature alignment in latent spaces, relying on the implicit assump…

• Sobek: Streaming Equivariant Tensor Product Convolutions

  Vladimir Choro\v{s}ajev, C\'edric B\'eny · 21 juillet 2026

  Equivariant graph neural networks repeatedly apply edge-conditioned tensor-product convolutions over graph edges. Conventional implementations materialize edge-specific weights, messages, and adjoints, causing tensor-product workspace and memory traffic to grow rapidly with graph size and operator w…

• An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation and Counterfactual Reasoning Evaluation

  Zhanbo Li, Shifeng Wu, Xiangjin Meng, Wenjie Cai · 21 juillet 2026

  Large language models encode world models implicitly in neural weights, which exposes four structural risks in high-precision domains such as medicine and finance: hallucination, frozen knowledge, poor explainability, and poor modifiability. This paper proposes data-first ontology: LLMs are treated …

• SAGA: Synthetic Agentic Graph Architecture for Temporal Benchmark Generation

  Jiacheng Ding, Xiaofei Zhang · 21 juillet 2026

  High quality temporal graph benchmarks with rich semantics and ground-truth anomaly labels are essential for training graph neural networks, yet remain scarce due to privacy constraints and annotation costs. We present SAGA (Synthetic Agentic Graph Architecture), a system for generating large-scale,…

• Natural Language Access to Domain-Specific Metadata: A Reusable Framework for LLM Query Generation

  Blake G. Fitch, Cato Elia Kurtz · 21 juillet 2026

  Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured queries on the metadata. We show that when domain vocabulary and semantics are captured in a well-designed Web Ontology Language (OWL) ontology, Large Language …

• On the Potential of Graph Neural Networks as Metamodels for Supply Chain Optimization: Dataset, Architectures, and Directions

  Tushar Lone, Neha Karanjkar · 21 juillet 2026

  Graph Neural Networks (GNNs) have emerged as a powerful, differentiable class of learning models for graph-structured systems. Their ability to generalize across topologies opens the prospect of a surrogate for combined structural and parametric optimization, which classical metamodels cannot offer.…

• Exact Network Surgery: Functional Invariance and Gradient Plasticity in Reactive Computational Graphs

  Abdallah Khemais (ISITCOM, University of Sousse) · 21 juillet 2026

  Function-preserving network growth techniques such as Net2Net and progressive stacking expand a model's capacity without destroying its learned function, but existing formulations either tolerate numerical perturbations or require a full rebuild of the training program. We formalize Exact Network Su…

• A Weisfeiler-Leman Characterization of Global-Attention Graph Transformers for Mixed-Integer Linear Programs

  Md Abrar Jahin, Craig A. Knoblock, Jay Pujara · 21 juillet 2026

  Graph foundation models (GFMs) with global attention are increasingly used to represent mixed-integer linear programs (MILPs), aiming to capture structure beyond the locality of standard graph neural networks. We study their expressive power through graph isomorphism testing, asking which MILP insta…

• Node4All: Learning Node Representation Beyond Datasets

  Dooho Lee, Jaemin Yoo · 21 juillet 2026

  Node representation learning has advanced rapidly, yet most existing methods rely on per-dataset training and hyperparameter tuning. This dataset-specific optimization comes from the difficulty of designing reusable graph models that generalize across diverse graph datasets. In this work, we introdu…

• PEARL: Auditable Repair for Scientific Reasoning Graph Extraction

  Bohan Su, Pengze Li, Yuchen Lu, Xi Chen · 21 juillet 2026

  Scientific Reasoning Graph Extraction (SRGE) aims to recover explicit links among observations, evidence, intermediate claims, and paper-level conclusions. LLMs can produce graph-like scientific explanations, but their outputs often mix malformed syntax, drifting edge labels, incorrectly oriented ro…

• A Survey on GNN-based Link Prediction: Techniques, Applications, and Challenges

  Chengcheng Sun, Yajie Song, Cheng Zhai, Jiayun Tian, Jia Yang, Xiaobin Rui, Jian Zhang, Zhixiao Wang, Philip S. Yu · 21 juillet 2026

  Graph Neural Networks (GNNs) have emerged as the leading paradigm for link prediction, enabling the inference of missing connections and the anticipation of potential future links. However, existing reviews lack systematic exploration specifically targeting underlying GNN architectures and diverse g…

• RADD: Retrieval-Augmented Discrete Diffusion for Multi-Modal Knowledge Graph Completion

  Guanglin Niu, Bo Li · 21 juillet 2026

  Most multi-modal knowledge graph completion (MMKGC) models use one embedding scorer to conduct both retrieval over the full entity set and final link prediction. We argue that this coupling is a core bottleneck: global high-recall search and local fine-grained disambiguation require different induct…

• MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

  Xu Hou, Meiyu Liang, Wei Huang, Yawen Li, Zhe Xue, Wu Liu, Guanhua Ye, Lei Shi, Kangkang Lu · 20 juillet 2026

  Multimodal Knowledge Graph Completion (MKGC) requires inferring missing entities from structural, textual, and visual cues. Existing diffusion-based MKGC methods usually denoise directly on raw multimodal features. Such a design forces the denoiser to simultaneously perform relation-dependent cue se…

• AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing

  Yuni Lai, Yulin Zhu, Yixuan Sun, Yulun Wu, Bin Xiao, Gaolei Li, Jianhua Li, Qi Xie, Kai Zhou · 20 juillet 2026

  Despite advancements in Graph Neural Networks (GNNs), adaptive attacks continue to challenge their robustness. Certified robustness via randomized smoothing offers provable guarantees but suffers from a severe accuracy-robustness trade-off, limiting its practical use. To bridge this gap, we introduc…

• Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework

  Xunkai Li, Guohao Fu, Yuming Ai, Zhengyu Wu, Hongchao Qin, Rong-Hua Li, Guoren Wang · 20 juillet 2026

  Multimodal-attributed graphs (MAGs), whose nodes carry modalities such as images and text alongside topological structure, now pervade applications including social platforms, e-commerce, and biomedical networks, offering richer semantic signals than single-modality graphs. In practice, such graphs …

• A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Data

  Raffaele Pojer, Andrea Passerini, Kim G. Larsen, Manfred Jaeger · 20 juillet 2026

  Graph neural networks (GNNs) excel at predictive tasks on graph-structured data but often lack the ability to incorporate symbolic domain knowledge and perform general reasoning. Relational Bayesian Networks (RBNs), in contrast, enable fully generative probabilistic modeling over graph-like structur…

• Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics

  Yuchang Zhu, Zezhong Xie, Huizhe Zhang, Huazhen Zhong, Jintang Li, Liang Chen, Zibin Zheng · 17 juillet 2026

  Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race. While this challenge has motivated extensive research, most existing solutions rely on the strong ass…

• Experience Memory Graph: One-Shot Error Correction for Agents

  Wenjun Wang, Yuchen Fang, Fengrui Liu, Zibo Liang, Kai Zheng · 16 juillet 2026

  Large Language Model (LLM) agents have shown remarkable capabilities in autonomous decision-making by generating sequential trajectories of states, actions, and observations. However, in complex, long-horizon tasks, these agents frequently suffer from compounding errors and struggle to recover from …

• MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model

  Charilaos Papaioannou, Ioannis Tsantilas, Dimitris Giannakakos, Vasilis Michalakopoulos, Sotiris Pelekis, Vangelis Marinakis, Arsam Aryandoust, Antonello Monti, Ricardo J. Bessa, Perdo P. Vergara, Jochen Cremer, Elissaios Sarmas · 16 juillet 2026

  Single-task fine-tuning of graph neural networks (GNNs) for power grid problems exhibits a systematic failure mode: models that achieve the lowest in-distribution error degrade the most under topology shift. We term this topology overfitting: the tendency of task-specific gradient signals to encode …

• Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs

  Mohammad Forouhesh · 16 juillet 2026

  Recovering a latent potential from observed flow on a directed graph (a discrete Poisson problem with Dirichlet boundaries) is ill-posed, and the standard fix backfires: ridge regularization shrinks toward a gauge-meaningless origin, collapsing and reversing the recovered ordering ($+0.81\to-0.42$ r…

• NodeImport: Imbalanced Node Classification with Node Importance Assessment

  Nan Chen, Zemin Liu, Bryan Hooi, Bingsheng He, Jun Hu, Jia Chen · 16 juillet 2026

  In real-world applications, node classification on graphs often faces the challenge of class imbalance, where majority classes dominate training, resulting in biased model performance. Traditional GNNs often struggle in such scenarios, as they tend to overfit to majority classes while underrepresent…