Social & Information Networks

Zehong Wang, Zheyuan Zhang, Chuxu Zhang et al.

This addresses the problem of slow inference in graph learning for applications like real-time fraud detection, offering a novel method that integrates structural information into MLPs, though it builds on prior distillation approaches.

Zhangyang Gao, Daize Dong, Cheng Tan et al.

This addresses a fundamental problem in graph modeling for domains like molecules, offering a novel approach to Euclideanize graphs with broad applications in representation and generation.

Ming Gu, Zhuonan Zheng, Sheng Zhou et al.

This work addresses a fundamental problem in graph machine learning for researchers and practitioners, offering a novel architecture to improve GNN universality across different graph types.

Zehong Wang, Zheyuan Zhang, Tianyi Ma et al.

It addresses scalability issues in graph learning for researchers and practitioners, offering a novel approach beyond message-passing.

Shijun Guo, Haoran Xu, Yaming Yang et al.

This addresses the challenge of efficient and non-intrusive opinion guidance for social network governance, representing a new paradigm rather than an incremental improvement.

Xingchao Jian, Purui Zhang, Lan Tian et al.

This addresses the challenge of tracking information or infection origins in networks for applications like misinformation and epidemiology, offering a novel statistical guarantee approach.

Zehong Wang, Zheyuan Zhang, Nitesh V Chawla et al.

This addresses the problem of building effective graph foundation models for applications like scientific research and drug discovery, representing a novel method for a known bottleneck.

Yifan Song, Fenglin Yu, Yihong Luo et al.

This addresses a critical issue for deploying graph learning systems in real-world applications like user profiling and cold-start recommendation, offering a novel solution to mitigate overfitting and distribution shifts.

Lianghao Xia, Ben Kao, Chao Huang

This addresses the problem of graph generalization for domains like recommendation systems and social network analysis, representing a novel method for a known bottleneck.

So Kuroki, Yingtao Tian, Kou Misaki et al.

This provides a rigorous, open-source foundation for building and evaluating LLM agents, aimed at fostering more cumulative and scientifically grounded research in multi-agent systems.

Ziwen Zhao, Yuhua Li, Yixiong Zou et al.

This work addresses the problem of learning topologically informative representations in graph self-supervised learning, offering a novel approach for researchers in graph neural networks.

Yibo Li, Xiao Wang, Hongrui Liu et al.

This work provides a foundational framework for understanding and designing GNNs, addressing a core theoretical gap in graph machine learning.

Xuanze Chen, Jiajun Zhou, Yadong Li et al.

This work addresses a significant problem in graph-based learning tasks, particularly for researchers and practitioners dealing with heterophilous graph structures, by providing a unified and principled approach for node classification.

Damiano Zanardini, Emilio Serrano

It addresses a novel problem in graph mining and social network analysis, focusing on zero-shot out-of-graph all-links prediction for isolated nodes.

Siqi Wang, Chao Liang, Yunfan Gao et al.

This work addresses challenges in urban industrial development for planners and operators, offering a novel integration of structured data and AI tools.

Jin-Duk Park, Jaemin Yoo, Won-Yong Shin

This work addresses the problem of efficient and accurate multi-criteria recommendation for e-commerce domains, which is significant for online retailers and consumers.

Nishant Vishwamitra, Keyan Guo, Farhan Tajwar Romit et al.

This addresses the critical threat of rapidly evolving online hate for internet users, representing a paradigm shift in moderation techniques.

Zehong Wang, Zheyuan Zhang, Chuxu Zhang et al.

This work addresses the problem of slow inference in graph learning for applications like real-time fraud detection, offering a novel method that is incremental in improving structural integration.

Hao Zhang, Xunkai Li, Yinlin Zhu et al.

This addresses data heterogeneity and privacy issues in federated graph learning for multi-client collaborative training, representing a novel paradigm rather than an incremental improvement.

Mathilde Perez, Raphaël Romero, Jefrey Lijffijt et al.

This work addresses the problem of understanding the impact of link prediction models on network structure for researchers and practitioners working with dynamic networks.