#Graph Neural Networks

Latest news articles tagged with "Graph Neural Networks". Follow the timeline of events, related topics, and entities.

Articles (10)

🇺🇸 Probing Graph Neural Network Activation Patterns Through Graph Topology — 25/02/2026 [USA]
arXiv:2602.21092v1 Announce Type: cross Abstract: Curvature notions on graphs provide a theoretical description of graph topology, highlighting bottlenecks and denser connected regions. Artifacts of ...
Related: #Graph Topology, #Machine Learning Research
🇺🇸 AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation — 20/02/2026 [USA]
arXiv:2602.17071v1 Announce Type: cross Abstract: Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies. T...
Related: #Adversarial Learning, #Heterophily, #Self‑Corrective Propagation, #Transformer Architectures
🇺🇸 Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning — 20/02/2026 [USA]
arXiv:2505.15547v3 Announce Type: replace-cross Abstract: After a renaissance phase in which researchers revisited the message-passing paradigm through the lens of deep learning, the graph machine le...
Related: #Message-Passing Limitation, #Oversmoothing, #Oversquashing, #Heterophily vs. Homophily
🇺🇸 Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning — 20/02/2026 [USA]
arXiv:2602.16947v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant ba...
Related: #Symbolic Machine Learning, #Expressivity Limits, #Interpretability, #Computational Efficiency
🇺🇸 From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection — 20/02/2026 [USA]
arXiv:2602.17342v1 Announce Type: cross Abstract: Graph Out-of-Distribution (OOD) detection aims to identify whether a test graph deviates from the distribution of graphs observed during training, wh...
Related: #Out‑of‑Distribution Detection, #Test‑Time Training, #Self‑Improving / Iterative Learning, #Prompt Engineering
🇺🇸 The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order Logic — 20/02/2026 [USA]
arXiv:2505.08021v4 Announce Type: replace Abstract: Graph Neural Networks (GNNs) address two key challenges in applying deep learning to graph-structured data: they handle varying size input graphs a...
Related: #First‑Order Logic, #Finite Model Theory, #Modal Logic, #Logical Expressiveness of Machine Learning Models
🇺🇸 GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning — 19/02/2026 [USA]
arXiv:2507.03267v2 Announce Type: replace Abstract: Dynamic Text-Attributed Graphs (DyTAGs), which intricately integrate structural, temporal, and textual attributes, are crucial for modeling complex...
Related: #Dynamic Graphs, #Text‑Attributed Graphs, #Generative Modeling, #Benchmark Development
🇺🇸 Expressive Power of Graph Transformers via Logic — 19/02/2026 [USA]
arXiv:2508.01067v2 Announce Type: replace-cross Abstract: Transformers are the basis of modern large language models, but relatively little is known about their precise expressive power on graphs. We...
Related: #Transformer Architecture, #Expressive Power Analysis, #Attention Mechanisms, #Theoretical vs Practical Evaluation
🇺🇸 MRC-GAT: A Meta-Relational Copula-Based Graph Attention Network for Interpretable Multimodal Alzheimer's Disease Diagnosis — 18/02/2026 [USA]
arXiv:2602.15740v1 Announce Type: cross Abstract: Alzheimer's disease (AD) is a progressive neurodegenerative condition necessitating early and precise diagnosis to provide prompt clinical management...
Related: #Neuroscience, #Artificial Intelligence, #Explainable AI, #Multimodal Data Integration
🇺🇸 SaVe-TAG: LLM-based Interpolation for Long-Tailed Text-Attributed Graphs — 16/02/2026 [USA]
arXiv:2410.16882v5 Announce Type: replace Abstract: Real-world graph data often follows long-tailed distributions, making it difficult for Graph Neural Networks (GNNs) to generalize well across both ...
Related: #Class Imbalance, #Text-Attributed Graphs