Infinite-Horizon Graph Filters: Leveraging Power Series to Enhance Sparse Information Aggregation
Key Laboratory of High Confidence Software Technologies (Peking University)(北京大学高可信软件技术重点实验室);University of Toronto(多伦多大学);Ministry of Education(教育部);School of Computer Science, Peking University(北京大学计算机学院);Big Data Technology Research Center, Nanhu Laboratory(南湖实验室大数据技术研究中心)
Graph Neural Networks (GNNs) have shown considerable effectiveness in a variety of graph learning tasks, particularly those based on the message-passing approach in recent years. However, their performance is often constrained by a limited receptive field, a challenge that becomes more acute in the presence of sparse graphs. In light of the power series, which possesses infinite expansion capabilities, we propose a novel Graph Power Filter Neural Network (GPFN) that enhances node classification by employing a power series graph filter to augment the receptive field. Concretely, our GPFN designs a new way to build a graph filter with an infinite receptive field based on the convergence power series, which can be analyzed in the spectral and spatial domains. Besides, we theoretically prove that our GPFN is a general framework that can integrate any power series and capture long-range dependencies. Finally, experimental results on three datasets demonstrate the superiority of our GPFN over state-of-the-art baselines.
All Nodes are created Not Equal: Node-Specific Layer Aggregation and Filtration for GNN
University of Science and Technology of China(中国科学技术大学);Tongji University(同济大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));University of Oxford(牛津大学);Griffith University(格里菲斯大学)
RMNA: A Neighbor Aggregation-Based Knowledge Graph Representation Learning Model Using Rule Mining
College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Remote Sensing and Information Engineering, Wuhan University(武汉大学遥感信息工程学院)
University of California Irvine(加州大学欧文分校);University of Rochester(罗切斯特大学)
图形是数学工具,可用于表示复杂的现实世界系统,如金融市场和社交网络。因此,图上的机器学习(ML)最近引起了极大的关注。然而,已经证明,ML over graphs放大了在各种决策问题中已经存在的对某些代表性不足的群体的偏见,这是由于有偏见的图结构上的信息聚合。面对这一挑战,在本文中,我们设计了一个公平的图过滤器,可以采用一种通用的方式为基于图的学习任务。建议的过滤器的设计是基于偏见分析和减轻偏见相比,其公平性不可知的对应建立其最优。在真实网络上进行节点分类的实验表明,所提出的滤波器设计在减轻偏差方面的有效性,同时与基线算法相比,获得了类似的实用性和更好的稳定性。
Multi-Step Model Predictive Safety Filters: Reducing Chattering by Increasing the Prediction Horizon
University of Toronto(多伦多大学);University of Toronto Robotics Institute(多伦多大学机器人研究所);Vector Institute for Artificial Intelligence(向量人工智能研究所);Technical University of Munich(慕尼黑工业大学);Munich Institute for Robotics and Machine Intelligence(慕尼黑机器人与机器智能研究所)
RaKUn: Rank-based Keyword extraction via Unsupervised learning and Meta vertex aggregation
Jožef Stefan International Postgraduate School(约瑟夫·斯特凡国际研究生院);Jožef Stefan Institute(约瑟夫·斯特凡研究所);Usher Institute, Medical School, University of Edinburgh(爱丁堡大学医学院厄舍研究所)