Advanced Graph Neural Networks

Derniers papiers

• Discovering the Representation Bottleneck of Graph Neural Networks

  Fang Wu, Siyuan Li, Stan Z. Li · 8 janvier 2026

  Graph neural networks (GNNs) rely mainly on the message-passing paradigm to propagate node features and build interactions, and different graph learning problems require different ranges of node interactions. In this work, we explore the capacity of GNNs to capture node interactions under contexts o…

• Inference Attacks Against Graph Generative Diffusion Models

  Xiuling Wang, Xin Huang, Guibo Luo, Jianliang Xu · 8 janvier 2026

  Graph generative diffusion models have recently emerged as a powerful paradigm for generating complex graph structures, effectively capturing intricate dependencies and relationships within graph data. However, the privacy risks associated with these models remain largely unexplored. In this paper, …

• Prompt Tuning without Labeled Samples for Zero-Shot Node Classification in Text-Attributed Graphs

  Sethupathy Parameswaran, Suresh Sundaram, Yuan Fang · 8 janvier 2026

  Node classification is a fundamental problem in information retrieval with many real-world applications, such as community detection in social networks, grouping articles published online and product categorization in e-commerce. Zero-shot node classification in text-attributed graphs (TAGs) present…

• IntroLM: Introspective Language Models via Prefilling-Time Self-Evaluation

  Hossein Hosseini Kasnavieh, Gholamreza Haffari, Chris Leckie, Adel N. Toosi · 8 janvier 2026

  A major challenge for the operation of large language models (LLMs) is how to predict whether a specific LLM will produce sufficiently high-quality output for a given query. Existing approaches rely on external classifiers, most commonly BERT based models, which suffer from limited context windows, …

• When Prompting Meets Spiking: Graph Sparse Prompting via Spiking Graph Prompt Learning

  Bo Jiang, Weijun Zhao, Beibei Wang, Jin Tang · 7 janvier 2026

  Graph Prompt Feature (GPF) learning has been widely used in adapting pre-trained GNN model on the downstream task. GPFs first introduce some prompt atoms and then learns the optimal prompt vector for each graph node using the linear combination of prompt atoms. However, existing GPFs generally condu…

• Multi-scale Graph Autoregressive Modeling: Molecular Property Prediction via Next Token Prediction

  Zhuoyang Jiang, Yaosen Min, Peiran Jin, Lei Chen · 7 janvier 2026

  We present Connection-Aware Motif Sequencing (CamS), a graph-to-sequence representation that enables decoder-only Transformers to learn molecular graphs via standard next-token prediction (NTP). For molecular property prediction, SMILES-based NTP scales well but lacks explicit topology, whereas grap…

• mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks

  Subhankar Mishra · 7 janvier 2026

  Graph Neural Networks (GNNs) suffer from over-smoothing in deep architectures and expressiveness bounded by the 1-Weisfeiler-Leman (1-WL) test. We adapt Manifold-Constrained Hyper-Connections (\mhc)~\citep{xie2025mhc}, recently proposed for Transformers, to graph neural networks. Our method, mHC-GNN…

• Temporal Graph Network: Hallucination Detection in Multi-Turn Conversation

  Vidhi Rathore, Sambu Aneesh, Himanshu Singh · 7 janvier 2026

  Hallucinations can be produced by conversational AI systems, particularly in multi-turn conversations where context changes and contradictions may eventually surface. By representing the entire conversation as a temporal graph, we present a novel graph-based method for detecting dialogue-level hallu…

• Recursive querying of neural networks via weighted structures

  Martin Grohe, Christoph Standke, Juno Steegmans, Jan Van den Bussche · 7 janvier 2026

  Expressive querying of machine learning models - viewed as a form of intentional data - enables their verification and interpretation using declarative languages, thereby making learned representations of data more accessible. Motivated by the querying of feedforward neural networks, we investigate …

• Heuristic Methods are Good Teachers to Distill MLPs for Graph Link Prediction

  Zongyue Qin, Shichang Zhang, Mingxuan Ju, Tong Zhao, Neil Shah, Yizhou Sun · 7 janvier 2026

  Link prediction is a crucial graph-learning task with applications including citation prediction and product recommendation. Distilling Graph Neural Networks (GNNs) teachers into Multi-Layer Perceptrons (MLPs) students has emerged as an effective approach to achieve strong performance and reducing c…

• TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer

  Yiwen Chen, Yiqing Wu, Huishi Luo, Fuzhen Zhuang, Deqing Wang · 7 janvier 2026

  Graph-based recommendation has achieved great success in recent years. The classical graph recommendation model utilizes ID embedding to store essential collaborative information. However, this ID-based paradigm faces challenges in transferring to a new domain, making it hard to build a pre-trained …

• Advanced Global Wildfire Activity Modeling with Hierarchical Graph ODE

  Fan Xu, Wei Gong, Hao Wu, Lilan Peng, Nan Wang, Qingsong Wen, Xian Wu, Kun Wang, Xibin Zhao · 6 janvier 2026

  Wildfires, as an integral component of the Earth system, are governed by a complex interplay of atmospheric, oceanic, and terrestrial processes spanning a vast range of spatiotemporal scales. Modeling their global activity on large timescales is therefore a critical yet challenging task. While deep …

• Semantic Alignment of Multilingual Knowledge Graphs via Contextualized Vector Projections

  Abhishek Kumar · 6 janvier 2026

  The paper presents our work on cross-lingual ontology alignment system which uses embedding based cosine similarity matching. The ontology entities are made contextually richer by creating descriptions using novel techniques. We use a fine-tuned transformer based multilingual model for generating be…

• Sparse Bayesian Message Passing under Structural Uncertainty

  Yoonhyuk Choi, Jiho Choi, Chanran Kim, Yumin Lee, Hawon Shin, Yeowon Jeon, Minjeong Kim, Jiwoo Kang · 6 janvier 2026

  Semi-supervised learning on real-world graphs is frequently challenged by heterophily, where the observed graph is unreliable or label-disassortative. Many existing graph neural networks either rely on a fixed adjacency structure or attempt to handle structural noise through regularization. In this …

• TT-FSI: Scalable Faithful Shapley Interactions via Tensor-Train

  Ungsik Kim, Suwon Lee · 6 janvier 2026

  The Faithful Shapley Interaction (FSI) index uniquely satisfies the faithfulness axiom among Shapley interaction indices, but computing FSI requires $O(d^\ell \cdot 2^d)$ time and existing implementations use $O(4^d)$ memory. We present TT-FSI, which exploits FSI's algebraic structure via Matrix Pro…

• From Mice to Trains: Amortized Bayesian Inference on Graph Data

  Svenja Jedhoff, Elizaveta Semenova, Aura Raulo, Anne Meyer, Paul-Christian B\"urkner · 6 janvier 2026

  Graphs arise across diverse domains, from biology and chemistry to social and information networks, as well as in transportation and logistics. Inference on graph-structured data requires methods that are permutation-invariant, scalable across varying sizes and sparsities, and capable of capturing c…

• Clinical Knowledge Graph Construction and Evaluation with Multi-LLMs via Retrieval-Augmented Generation

  Udiptaman Das, Krishnasai B. Atmakuri, Duy Ho, Chi Lee, Yugyung Lee · 6 janvier 2026

  Large language models (LLMs) offer new opportunities for constructing knowledge graphs (KGs) from unstructured clinical narratives. However, existing approaches often rely on structured inputs and lack robust validation of factual accuracy and semantic consistency, limitations that are especially pr…

• A Knowledge Graph and Deep Learning-Based Semantic Recommendation Database System for Advertisement Retrieval and Personalization

  Tangtang Wang, Kaijie Zhang, Kuangcong Liu · 6 janvier 2026

  In modern digital marketing, the growing complexity of advertisement data demands intelligent systems capable of understanding semantic relationships among products, audiences, and advertising content. To address this challenge, this paper proposes a Knowledge Graph and Deep Learning-Based Semantic …

• Learning from Historical Activations in Graph Neural Networks

  Yaniv Galron, Hadar Sinai, Haggai Maron, Moshe Eliasof · 6 janvier 2026

  Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains such as social networks, molecular chemistry, and more. A crucial component of GNNs is the pooling procedure, in which the node features calculated by the model are combined to form an informative final descriptor t…

• Accelerating Storage-Based Training for Graph Neural Networks

  Myung-Hwan Jang, Jeong-Min Park, Yunyong Ko, Sang-Wook Kim · 6 janvier 2026

  Graph neural networks (GNNs) have achieved breakthroughs in various real-world downstream tasks due to their powerful expressiveness. As the scale of real-world graphs has been continuously growing, \textit{a storage-based approach to GNN training} has been studied, which leverages external storage …

• Learning Resilient Elections with Adversarial GNNs

  Hao Xiang Li, Yash Shah, Lorenzo Giusti · 6 janvier 2026

  In the face of adverse motives, it is indispensable to achieve a consensus. Elections have been the canonical way by which modern democracy has operated since the 17th century. Nowadays, they regulate markets, provide an engine for modern recommender systems or peer-to-peer networks, and remain the …

• Reinforcement Learning Enhanced Multi-hop Reasoning for Temporal Knowledge Question Answering

  Wuzhenghong Wen, Chao Xue, Su Pan, Yuwei Sun, Minlong Peng · 6 janvier 2026

  Temporal knowledge graph question answering (TKGQA) involves multi-hop reasoning over temporally constrained entity relationships in the knowledge graph to answer a given question. However, at each hop, large language models (LLMs) retrieve subgraphs with numerous temporally similar and semantically…

• What Breaks Knowledge Graph based RAG? Empirical Insights into Reasoning under Incomplete Knowledge

  Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Yuan He, Jiaoyan Chen, Steffen Staab, Evgeny Kharlamov · 6 janvier 2026

  Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the structured evidence of knowledge graphs. However, current evaluation practices fall short: existing benchmarks often include q…

• Distribution Matching for Graph Quantification Under Structural Covariate Shift

  Clemens Damke, Eyke H\"ullermeier · 6 janvier 2026

  Graphs are commonly used in machine learning to model relationships between instances. Consider the task of predicting the political preferences of users in a social network; to solve this task one should consider, both, the features of each individual user and the relationships between them. Howeve…

• Robust Graph Fine-Tuning with Adversarial Graph Prompting

  Ziyan Zhang, Bo Jiang, Jin Tang · 5 janvier 2026

  Parameter-Efficient Fine-Tuning (PEFT) method has emerged as a dominant paradigm for adapting pre-trained GNN models to downstream tasks. However, existing PEFT methods usually exhibit significant vulnerability to various noise and attacks on graph topology and node attributes/features. To address t…