arxivJul 13bullish

Model Agnostic Graph Prompt Learning for Crystal Property Prediction

arXiv:2607.08996v1 Announce Type: cross Abstract: Graph Neural Networks have emerged as a powerful tool for the fast and accurate prediction of various crystal properties. These models often encode domain-specific knowledge into their graph encoding modules, which increases their parameter size and

GR1 model #graph-neural-networks #crystal-properties #prompt-learning Read on arxiv →

arxivJun 18bullish

Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS

arXiv:2606.18287v1 Announce Type: new Abstract: Multimodal neuroimaging, integrating functional connectivity from fMRI and structural connectivity from DTI, enables non-invasive analysis of brain networks using graph neural networks. However, demographic factors such as age and sex systematically co

AR1 model #neuroimaging #graph-neural-networks #causality Read on arxiv →

arxivJun 12bullish

A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction

arXiv:2606.12673v1 Announce Type: cross Abstract: Cross-domain graph anomaly detection (GAD) aims to identify abnormal nodes in unseen target graphs, showing strong potential in real-world applications with heterogeneous graph data. However, existing methods often depend on dataset-specific feature

AL1 model #anomaly-detection #graph-neural-networks #zero-shot-learning Read on arxiv →

arxivMay 26bullish

'Si'multaneous 'S'patial-'T'emporal Message Passing for Dynamic Graph Representation Learning

arXiv:2605.25548v1 Announce Type: cross Abstract: Dynamic graph neural networks (DGNNs) that operate on snapshot sequences typically fall into one of two categories. \emph{Temporal-first} approaches build per-node temporal embeddings and only afterwards perform spatial aggregation, whereas \emph{Spa

SI1 model #machine-learning #graph-neural-networks #link-prediction Read on arxiv →

arxivMay 25bullish

Graph Alignment Topology as an Inductive Bias for Grounding Detection

arXiv:2605.22963v1 Announce Type: cross Abstract: Large Language Models (LLMs) are optimized to produce distributionally plausible continuations rather than to explicitly verify whether generated propositions are entailed by source documents. This inductive bias enables generalization, but it does n

GP1 model #large-language-models #factuality #graph-neural-networks Read on arxiv →

arxivMay 16

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors

arXiv:2605.08278v2 Announce Type: replace-cross Abstract: GNNs have become a standard tool for learning on relational data, yet they remain highly vulnerable to backdoor attacks. Prior defenses often depend on inspecting specific subgraph patterns or node features, and thus can be circumvented by ad

#graph-neural-networks #backdoor-attacks #security Read on arxiv →

arxivMay 7bullish

Joint Relational Database Generation via Graph-Conditional Diffusion Models

arXiv:2505.16527v3 Announce Type: replace Abstract: Building generative models for relational databases (RDBs) is important for many applications, such as privacy-preserving data release and augmenting real datasets. However, most prior works either focus on single-table generation or adapt single-t

GR1 model #relational-databases #generative-models #graph-neural-networks Read on arxiv →