Advanced Graph Neural Networks

Neueste Paper

• Graph Neural Networks for the Graphical Bootstrap

  Rigers Aliaj, Gabriele Dian, Reza Doobary, Paul Heslop · 7. Juli 2026

  We study a graph classification problem involving over 20 million graphs, arising from high-order perturbative computations of correlators in planar $\mathcal{N}=4$ super-Yang--Mills, a model closely related to the theory of the strong nuclear force. We benchmark graph neural networks, including gra…

• Semi-parametric Functional Classification via Path Signatures Logistic Regression with Adaptive Order Selection

  Pengcheng Zeng, Siyuan Jiang · 7. Juli 2026

  We propose Path Signatures Logistic Regression (PSLR), a semi-parametric framework for classifying vector-valued functional data with scalar covariates. Classical functional logistic regression models rely on linear assumptions and fixed basis expansions, which limit flexibility and degrade performa…

• Foundations of Equivariant Deep Learning: Unifying Graph and Sheaf Neural Networks

  Yoshihiro Maruyama · 7. Juli 2026

  Symmetry is everywhere in nature and society. Geometric deep learning exploits symmetries in data to improve the performance and efficiency of deep learning systems. In this paper, we extend geometric deep learning to utilize richer symmetry structures. Specifically, we develop order-equivariant neu…

• TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction

  Mouhamed Amine Bouchiha, Gregory Blanc · 7. Juli 2026

  Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated analysis and reasoning. Cybersecurity Knowledge Graphs (CSKGs) provide a structured representation of adversarial entities, actions, and relations, but …

• PIEFS: Physics-Informed Eigenfunction Features with Learnable Scaling

  Varvara Nazarenkko, Timur Lidzhiev, Alexander Tarakanov · 7. Juli 2026

  Spectral methods are widely used to construct representations from the geometry of data, but they often rely on a fixed kernel, graph Laplacian, or manually selected feature scaling. We propose Physics-Informed Eigenfunction Features with Learnable Scaling (PIEFS), a supervised neural representation…

• Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls

  Kirill Shevkunov, Andrey Ploskonosov, Liudmila Prokhorenkova · 7. Juli 2026

  In many machine learning applications, the most relevant items for a query should be efficiently retrieved. The relevance function is usually an expensive similarity model, making the exhaustive search infeasible. A typical solution is to train another model that separately embeds queries and items …

• TRIAGE: Trustworthy Retrieval Instrumentation And Graph Evaluation

  Axel TahmasebiMoradi, Lucas Schott, Martin Royer · 7. Juli 2026

  Knowledge graphs (KGs) that underpin Graph-based Retrieval-Augmented Generation (Graph-RAG) are increasingly built automatically by LLM-driven extraction rather than curated by experts. Proper evaluation would require instrumenting all pertinent stages: extraction, graph construction, and inference,…

• On Preserving Geometrical Invariance for Superpixel Image Classification using Graph Transformer

  Sarabeshwar Balaji, Shubham Mohanty, Akash Anil · 7. Juli 2026

  Convolutional Neural Network (CNN) and Vision Transformer (ViT) for image classification exploit a dense grid of pixels containing redundant information. Consequently, for a larger image dataset, CNNs and ViTs face deployability challenges due to high computational complexity. Representing images as…

• Poisson-Gamma Modeling of Inter-Relational Dependencies in Dynamic Knowledge Graphs

  Nan Fang, Yijun Wang, Hao Liao, Sikun Yang · 7. Juli 2026

  Dynamic knowledge graphs are ubiquitous in today's AI applications, as we represent molecular structures, social relationships, and language information using these graph models. As knowledge graphs evolve over time and are often noisy and incomplete, modeling their temporal and relational dependenc…

• Conditional Diffusion Guided Knowledge Transfer for Multi-Domain Knowledge Graph Completion

  Jiawei Sheng, Taoyu Su, Xixun Lin, Xiaodong Li, Tingwen Liu · 7. Juli 2026

  Multi-domain knowledge graph completion (MKGC) aims to improve missing triple prediction in a target KG by transferring knowledge from other support KGs. Existing methods typically enforce consistency constraints on equivalent entities across KGs to transfer knowledge, which risks suppressing domain…

• Heterogeneous Graph Condensation via Role-Aware Clustering

  Fuyan Ou, Yulin Hu, Ye Yuan · 7. Juli 2026

  Heterogeneous Graph Neural Networks (HGNNs) have exhibited remarkable efficacy in modeling complex systems with multiple types of nodes and relations, yet their training on large-scale heterogeneous graphs remains computationally prohibitive. Although graph condensation methods can effectively impro…

• Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation

  Wenda Wang, Jinjia Feng, Zhewei Wei · 7. Juli 2026

  Recent advances in molecular large language models have led to strong performance on molecular understanding and generation tasks, yet these gains often come without reliable structural grounding. In particular, existing approaches conflict with the chemistry principle that structure determines func…

• Graph Classification via Network Usable Information: From Representation Evaluation to Structure Selection

  Abdullah Shaik, Anwar Said · 7. Juli 2026

  We propose NetinfoGC, a framework for graph classification that extends the Network Usable Information (NUI) paradigm to graph-level learning. Unlike conventional graph neural network approaches that rely on end-to-end training of black-box embeddings, NetinfoGC constructs a family of permutation-in…

• A Near-Linear-Time Solver for Graph $p$-Laplacian Semi-Supervised Learning via Continuation in $p$

  Oren E. Livne · 7. Juli 2026

  Graph-based semi-supervised learning (SSL) propagates a few labels over a similarity graph by minimizing a Dirichlet-type energy. The standard quadratic ($p=2$) energy reduces to a single graph-Laplacian solve, but it degenerates exactly where SSL is most useful when labels are scarce: gathering mor…

• FAST: A Holistic Framework for Optimizing Memory-I/O, Computation, and Sampling in Temporal GNN Training

  Yushu Cai, Qingrui Zhu, Lei Liu, Kai Sheng, Hao Chen, Xin He · 7. Juli 2026

  Temporal Graph Neural Networks (TGNNs) are widely used for learning from dynamic graphs in applications such as recommendation, social network analysis, and traffic forecasting. However, scaling TGNN training to large dynamic graphs remains challenging due to three intertwined bottlenecks: memory I/…

• MeGA-MP: Metric Graph Advection Message Passing -- A Physics-Informed Message Passing Operator for Advection-Dominated Metric Graphs

  Janine Strotherm, Luca Hermes, Andr\'e Artelt, Barbara Hammer · 7. Juli 2026

  Many real-world systems are organized as networks where spatio-temporal dynamics unfold along connections and not discretely between nodes. Examples include utility networks such as water distribution systems or gas networks, electrical grids, and traffic flow networks. Such systems are naturally mo…

• Hyperparameter Transfer in Graph Neural Networks

  Gage DeZoort, Boris Hanin · 7. Juli 2026

  The performance of deep learning models crucially depends on the settings of hyperparameters like learning rate, initialization scale, and weight decay. Hyperparameter transfer aims to make near-optimal hyperparameter settings consistent across model scale, so that large models can be optimized by p…

• Target-Aware Interaction-Guided Reinforcement Learning for Black-Box Node Injection Attacks on Graph Neural Networks

  Yi Lan, Ye Yuan · 7. Juli 2026

  Graph Neural Networks (GNNs) have achieved remarkable performance in graph representation learning, yet their inherent vulnerability to adversarial attacks poses severe security risks. Especially, black-box node injection attacks have become a major threat to GNNs since they inject malicious nodes w…

• FLASH: Flexible Learning of Adaptive Sampling from History in Temporal Graph Neural Networks

  Or Feldman, Krishna Sri Ipsit Mantri, Carola-Bibiane Sch\"onlieb, Chaim Baskin, Moshe Eliasof · 7. Juli 2026

  Aggregating temporal signals from historic interactions is a key step in future link prediction on dynamic graphs. However, incorporating long histories is resource-intensive. Hence, temporal graph neural networks (TGNNs) often rely on historical neighbors sampling heuristics such as uniform samplin…

• Trust Region Policy Distillation

  Zhengpeng Xie, Li Lyna Zhang, Zeke Xie, Mao Yang · 7. Juli 2026

  Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust Region Policy Distillation (TOP-D), which transforms the notoriously unstable, high-variance On-Policy Distillation (OPD) into a stable training paradigm by dynamically constructing a proximal teache…

• MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning

  Yaniv Shulman, Shaghayegh Akbarpour, Jack B. Muir · 7. Juli 2026

  We propose MABLE (Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning), a self-supervised framework for learning node and graph embeddings from large, heterogeneous graphs, demonstrated here on geospatial mineral-exploration data. MABLE combines masked reconstruct…

• EO-Agents: A Three-Agent LLM Pipeline for Earth Observation Hypothesis Generation

  Mahyar Ghazanfari, Amin Tabrizian, Armin Mehrabian, Peng Wei · 3. Juli 2026

  Large language models have recently been explored for scientific hypothesis generation, but most prior work relies on unstructured literature and free-form textual claims. We present a pipeline for Earth observation that grounds hypothesis generation directly in the NASA Earth Observation Knowledge …

• IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs

  Samir Abdaljalil, Erchin Serpedin, Hasan Kurban · 3. Juli 2026

  We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates reasoning ability from domain knowledge retrieval in LLM evaluation. Each pair shares identical logical structure but requires different domain-specific knowledge, enabling controlled attribution of reas…

• Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization

  Jan Drchal · 3. Juli 2026

  Large language models (LLMs) are often asked to produce JSON conforming to a fixed schema, powering information extraction, tool calling, agentic planning, and knowledge-graph construction. Measuring how closely an output matches a gold reference is essential yet surprisingly hard: exact match is br…

• Embedding Inference Attack

  Cedric Fitiavana Raelijohn, S\'ebastien Gambs, Jean-Francois Rajotte · 3. Juli 2026

  Embedding models are essential components of modern Information Retrieval (IR) systems, yet they are typically hidden behind APIs. Recent works have shown that dense IR system can lead to security vulnerabilities such as embedding inversion attacks. However, such attacks usually require that the att…