The paper reinterprets graph neural networks (GNNs) as retrieval-augmented models, where each layer uses an MLP on a node representation and a permutation‑invariant summary of retrieved graph context instead of traditional message passing. It introduces RTA, a lightweight MLP‑based framework that replaces structural message passing with label‑aware retrieval and propagation, and provides theoretical links to softmax‑attention message passing and robustness to mis‑retrieved outliers. Experiments on text‑attributed graph benchmarks demonstrate that RTA matches or surpasses strong GNN and graph LLM baselines while improving efficiency and robustness.
By Jintang Li, Yuhong Chen, Ruofan Wu, Binli Luo, Jiayi Ji, Hui Li, Rongrong Ji
arXiv:2601. 19449v2 Announce Type: replace Abstract: Graph neural networks (GNNs) are widely believed to excel at node representation learning through trainable neighborhood aggregations.
By Celia Rubio-Madrigal, Rebekka Burkholz
arXiv:2511. 11046v3 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) have become an indispensable tool for analyzing relational data.
By Brian Godwin Lim, Galvin Brice Lim, Renzo Roel Tan, Irwin King, Kazushi Ikeda
DeltaGNN introduces an information flow control mechanism that uses a new connectivity measure, the information flow score, to mitigate over‑smoothing and over‑squashing in Graph Neural Networks. This approach enables linear computational and memory overhead while effectively capturing both short‑range and long‑range node interactions. Experiments on ten diverse real‑world datasets demonstrate superior performance with limited computational complexity.
By Kevin Mancini, Islem Rekik
arXiv:2608. 02168v1 Announce Type: new Abstract: Credit risk detection, particularly mitigating individual fraud, is crucial for maintaining the stability of digital financial ecosystems.
By Xin Liu, Xiyuan Chen, Chenglong Wu, Xuan Zong, Jun Zhou, Dawei Cheng
Credit risk detection, particularly mitigating individual fraud, is crucial for maintaining the stability of digital financial ecosystems. Accurately identifying credit fraud among billions of users is critical for minimizing financial losses and safeguarding the sustainability of inclusive financial services.
arXiv:2608. 02128v1 Announce Type: new Abstract: Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers.
By Antonin Joly, Nicolas Keriven, Aline Roumy
The paper presents a scalable graph neural network (GNN) system for friend recommendation on a massive social graph. It introduces two key design choices: multi-hash ID embeddings that shrink the embedding table by over 98% without hurting ranking quality, and a timestamp-sorted compressed sparse row (CSR) storage with binary search that reduces temporal neighbor sampling from linear to logarithmic time. Experiments on a 194‑million‑user, 28‑billion‑edge graph show that these techniques enable production‑grade performance, boosting friend additions by 16% and unique friend adders by 11.5% in an online A/B test.
By Maksim Utushkin, Andrei Ovsiannikov, Alexander D'yakonov
GraphIFE addresses the class imbalance problem in graph-structured data by tackling a quality inconsistency issue in synthesized nodes. The framework uses graph invariant learning to strengthen embedding space representations and identify invariant features, leading to improved performance on minority classes. Experiments show that GraphIFE consistently outperforms various baselines across multiple datasets.
By Fanlong Zeng, Wensheng Gan, Kangjie Chen, Philip S. Yu
Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers. We show that several existing scalable approaches can be written as structured modifications of the GNN propagation matrix, providing a unified perspective that exposes their respective limitations.
GraphFAS is a distributed system that automates graph feature generation and selection for industrial transaction networks. It uses a non‑parametric module to create explicit, interpretable structural features through multi‑hop subgraph extraction and multi‑scale aggregation, and extends the Boruta algorithm with median‑based aggregation across partitions for robust feature selection. The approach decouples feature aggregation from model training, allowing integration with tabular models and TreeSHAP explanations, and has been deployed in Alipay, yielding significant engineering efficiency gains and strong performance against expert‑driven and graph‑learning baselines.
By Yice Luo, Yun Zhu, Xi Chen, Yongchao Liu, Xintan Zeng, Chengying Huan, Kai Zhang, Jinrui Zhang, Juelu Zhang, Jiajun Zheng
arXiv:2609.06154v1 Announce Type: new
Abstract: One-shot federated graph learning generally aims to train Graph Neural Networks (GNNs) across clients with disconnected subgraphs in a single communica...
By Shutong Zheng, Sijia Chen