Advanced Graph Neural Networks

Latest papers

• Amortized Maximum Inner Product Search with Learned Support Functions

  Theo X. Olausson, Jo\~ao Monteiro, Michal Klein, Marco Cuturi · 2 July 2026

  Maximum inner product search (MIPS) is a crucial subroutine in machine learning, requiring the identification of a vector taken within a database (the keys) that best aligns with a given query. We propose amortized MIPS: a regression-based approach that trains neural networks to directly predict MIP…

• Relevance Is Not Permission: Warranted Attention for Value Contributions

  Minwoo Yu, Young-guk Ha · 2 July 2026

  Relevance is not permission. Attention lets a model read key-value items related to the current query, but it does not guarantee that the value contribution of such an item becomes prediction evidence. A retrieved passage may be relevant to a question without being supporting evidence, and a histori…

• Multi-Label Node Classification with Label Influence Propagation

  Yifei Sun, Zemin Liu, Bryan Hooi, Yang Yang, Rizal Fathony, Jia Chen, Bingsheng He · 2 July 2026

  Graphs are a complex and versatile data structure used across various domains, with possibly multi-label nodes playing a particularly crucial role. Examples include proteins in PPI networks with multiple functions and users in social or e-commerce networks exhibiting diverse interests. Tackling mult…

• SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport

  Yuting Zhang, Yanbei Liu, Zhitao Xiao, Lei Geng, Yanwei Pang, Xiao Wang · 2 July 2026

  Self-supervised Continual Graph Learning (CGL) aims to successively learn from a graph sequence with different tasks without label supervision - a paradigm that has attracted widespread attention. Most existing self-supervised CGL methods rely on instance-level consistency objectives that enforce st…

• CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models

  Qizhi Jiang, Shuo Wang, Pei Ke, Yuhang Song, Ke Qin · 2 July 2026

  Large Reasoning Models (LRMs) have achieved remarkable success on complex tasks by leveraging long chain-of-thought (CoT) trajectories, yet they frequently exhibit overthinking on simple queries, resulting in significant token overhead and reduced inference efficiency. However, existing compression …

• AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

  Bao Long Nguyen Huu, Atsushi Hashimoto · 2 July 2026

  GraphRAG is an extension of retrieval-augmented generation (RAG) that supports large language models (LLMs) by referring to graph-structured data as external knowledge. While this technique ideally captures intricate relationships, it often struggles with graph representations for LLMs, particularly…

• Beyond Triplet Plausibility: Relation Set Completion in Knowledge Graphs

  Zihao Zheng, Borui Cai, Yao Zhao, Keshav Sood, Yong Xiang · 1 July 2026

  Knowledge graphs (KGs) organize real-world knowledge as triplets and underpin many downstream applications. Due to their inherent incompleteness, knowledge graph completion (KGC) is widely studied and is typically formulated as triplet prediction, with link prediction as the dominant paradigm. Howev…

• FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning

  Zekai Chen, Kairui Yang, Xuaner Chen, Xunkai Li, Xun Wu, Rong-Hua Li, Guoren Wang · 1 July 2026

  Multimodal graph foundation models aim to learn reusable knowledge from graphs enriched with text, images, attributes, and relational topology, thereby supporting diverse graph-centric and modality-centric tasks. In practice, however, such multimodal graphs are often distributed across decentralized…

• Measuring Graph-to-Graph Semantic Similarity in Knowledge Graphs: An Empirical Evaluation of Knowledge Graph Embeddings

  Seungryeol Baek, Wooseok Sim, Hogun Park · 1 July 2026

  A Knowledge Graph (KG) represents facts as structured triples and is widely used to organize relational knowledge across diverse domains. Just as textual information ranges from words and sentences to complete documents, KG information can be interpreted at multiple levels, from entities, relations,…

• TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning

  Lingjie Chen, Yuanchen Bei, Haobo Xu, Yanjun Zhao, Yuzhong Chen, Hanghang Tong · 1 July 2026

  Text-attributed graphs (TAGs), where each node carries a natural language description, require models to jointly reason over text and graph topology. Existing approaches often handle the two modalities separately: graph neural networks operate on shallow text features, while hybrids of LLMs and grap…

• ComplianceGate: Classifier-Gated Multi-Tier LLM Routing for Inference in Regulated Industries

  Abhishek Dey · 1 July 2026

  Large language models deployed in regulated industries operate under two constraints: compliance enforcement and cost efficiency. Personally identifiable information (PII) in user queries can reach model endpoints before the system determines whether that data should leave its jurisdictional boundar…

• Nazrin: An Atomic Neural Proof Automation Tactic in Lean 4

  Leni Aniva, Iori Oikawa, David Dill, Clark Barrett · 1 July 2026

  In Machine-Assisted Theorem Proving, a theorem proving agent searches for a sequence of expressions and tactics that can prove a statement in a proof assistant. In this work, we introduce several novel concepts and capabilities to address obstacles faced by machine-assisted theorem proving. We first…

• The Impact of Dimensionality on the Stability of Node Embeddings

  Tobias Schumacher, Simon Reichelt, Markus Strohmaier · 1 July 2026

  Previous work has shown that node embedding methods can produce different representations and downstream predictions across repeated training runs, even when trained on the same data with identical hyperparameters. However, the role of embedding dimensionality in this instability remains poorly unde…

• Learning to Select, Not Relearn: Hard-Routed Mixtures of Reasoning LoRAs

  Seyed Alireza Molavi, Zhan Su, Yan Hu, Peyman Sheikholharam Mashhadi, Stefan Byttner, Prayag Tiwari · 1 July 2026

  Composing independently trained LoRA adapters into a single large language model is useful for multi-domain adaptation, especially when the original training data cannot be shared. A common approach is to use MoE-style routing over LoRA experts, but for frozen pretrained adapters, soft weighted comb…

• Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs

  Feifan Wang · 30 June 2026

  Detecting communities in heterophilic graphs -- where connected nodes often belong to different classes -- is hard for unsupervised methods: classical modularity and spectral methods are feature agnostic, while deep graph-clustering methods rely on contrastive or generative machinery that is opaque.…

• KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models

  Boshko Koloski, Xiangjian Jiang, Senja Pollak, Bla\v{z} \v{S}krlj, Mateja Jamnik, Nikola Simidjievski · 30 June 2026

  Tabular foundation models have advanced deep learning for tabular data by delivering strong default performance across many small and medium tasks. Yet in niche domains, where data is scarce, high-dimensional, and shifted from the pretraining distribution, they may still fail to outperform carefully…

• Never Skip a Batch: Dense Learning of Temporal GNNs via Adaptive Pseudo-Supervision

  Alexander Panyshev, Dmitry Vinichenko, Oleg Travkin, Roman Alferov, Alexey Zaytsev · 30 June 2026

  Temporal graph networks suffer from irregular supervision in realworld dynamic graphs, as most minibatches contain few labeled events. The lack of labels leads to high-variance gradient updates and, consequently, slow wall-clock convergence. To constructively reduce sparsity, our Moving-Averaged Lab…

• T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation

  Huy Truong, Alexander Lazovik, Victoria Degeler · 30 June 2026

  Graph Neural Networks (GNNs) deployed in real-world systems typically have fixed weights, often leading to degraded performance under distribution shifts. This issue can be mitigated by conventional fine-tuning, but in many real-world cases, collecting labeled data is expensive or infeasible. A pote…

• First-Order Temporal Logic Tensor Networks

  Luca Boscarato, Ivan Donadello, Alessandro Artale, Marco Montali, Fabrizio Maria Maggi · 30 June 2026

  Most of the existing neuro-symbolic AI methods focus on the scenario of static knowledge where objects do not change according to a temporal dimension. Temporal neuro-symbolic works are still under explored and are mainly developed for time-interval logic or propositional linear temporal logic. Ther…

• Blackknife: Hard-Label Query-Limited Black-Box Attacks on Heterogeneous Graph Neural Networks

  Honglin Gao, Junhao Ren, Lan Zhao, Yue Yang, Jindong Chang, Gaoxi Xiao · 30 June 2026

  Heterogeneous graph neural networks (HGNNs) have achieved strong performance in modeling complex graph-structured data with multiple node and relation types. However, their robustness under realistic black-box adversarial settings remains insufficiently explored. Existing attacks on HGNNs usually as…

• Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting

  Peyman Baghershahi, Sourav Medya · 30 June 2026

  Prompt tuning has become a key mechanism for adapting pre-trained Graph Neural Networks (GNNs) to new downstream tasks. However, existing approaches are predominantly supervised, relying on labeled data to optimize the prompting parameters and typically fine-tuning a task-specific prediction head --…

• Rethinking Generative Reconstruction Attacks against Graph Neural Network Models

  Adebayo Keji, Sayanton Dibbo · 30 June 2026

  The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive. The non-Euclidean nature of the graph data makes the analysis computationally challenging, leading to the use of Graph Neural Networks (GNNs…

• DyGnROLE: Asymmetric Pretraining for Edge Classification on Dynamic Graphs

  Tyler Bonnet, Marek Rei · 30 June 2026

  Edge classification on directed dynamic graphs requires modeling interactions between source and destination nodes exhibiting asymmetrical behavioral patterns and temporal dynamics. However, existing dynamic graph architectures largely rely on shared parameters for processing source and destination …

• Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs

  Illia Makarov, Mykola Glybovets · 30 June 2026

  Retrieval-augmented generation built on knowledge graphs (Graph RAG) outperforms flat passage retrieval on multi-hop question answering by leveraging graph structure. In most existing systems, however, the question only sets the seed nodes; the subsequent traversal becomes "query-blind", depending s…

• Attention Enhanced Entity Recommendation for Intelligent Monitoring in Cloud Systems

  Fiza Husain, Anson Bastos, Anjaly Parayil, Ayush Choure, Chetan Bansal, Rujia Wang, Saravan Rajmohan · 30 June 2026

  In this paper, we present DiRecGNN, an attention-enhanced entity recommendation framework for monitoring cloud services at Microsoft. We provide insights on the usefulness of this feature as perceived by the cloud service owners and lessons learned from deployment. Specifically, we introduce the pro…