几篇最新的arXiv论文探讨了图神经网络（GNNs）的进展和挑战。研究内容包括验证GNN归属和检测仿冒模型的方法，以及开发用于评估知识图谱构建和GNN性能的统一基准。其他工作则侧重于对抗性GNNs的标准化评估协议、用于缓解过挤压和过平滑的图重连技术调查、自适应节点特征选择，以及一个名为Grothendieck Graph Neural Networks的新代数框架，该框架超越了传统的基于邻域的聚合。
AI
arXiv:2605.05360v1 Announce Type: new Abstract: Given two GNNs that output node embeddings, how can we determine if they were trained independently? An adversary could have trained one GNN specifically to mimic the other GNN's embeddings. To obscure this relationship between the …
arXiv cs.LG
TIER_1English(EN)·Tran Gia Bao Ngo, Zulfikar Alom, Federico Errica, Murat Kantarcioglu, Cuneyt Gurcan Akcora·
arXiv:2605.05534v1 Announce Type: new Abstract: Adversarial learning and the robustness of Graph Neural Networks (GNNs) are topics of widespread interest in the machine learning community, as documented by the number of adversarial attacks and defenses designed for these purposes…
arXiv:2605.05476v1 Announce Type: new Abstract: Knowledge graphs automatically constructed from text are increasingly used in real-world applications. However, their inherent noise, fragmentation, and semantic inconsistencies significantly affect the performance of Graph Neural N…
arXiv:2605.00951v1 Announce Type: new Abstract: Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, …
arXiv cs.LG
TIER_1English(EN)·Ali Azizpour, Madeline Navarro, Santiago Segarra·
arXiv:2510.03096v2 Announce Type: replace Abstract: We propose an adaptive node feature selection approach for graph neural networks (GNNs) that identifies and removes unnecessary features during training. The ability to measure how features contribute to model output is key for …
arXiv:2411.17429v2 Announce Type: replace Abstract: Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compress…
arXiv:2604.25978v1 Announce Type: cross Abstract: Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. For a fixed graph, one would then expect GNNs traine…
arXiv cs.LG
TIER_1English(EN)·Amirreza Shiralinasab Langari, Leila Yeganeh, Kim Khoa Nguyen·
arXiv:2412.08835v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) are almost universally built on a single primitive: the neighborhood. Regardless of architectural variations, message passing ultimately aggregates over neighborhoods, which intrinsically limits expr…
