Sigma Ouc This research domain focuses on developing scalable gnn architectures tailored for complex graph networks with billions of nodes edges, while enhancing performance across diverse graph mining tasks such as recommendation systems, anomaly detection, and beyond. In this paper, we propose sigma, a similarity based aggregation for heterophilous graph neural network. we derive a new interpretation of simrank as global gnn aggregation, highlighting its capability of discovering similarity among all node pairs, suitable for heterophily graphs.
Sigma Ouc This research domain focuses on developing scalable gnn architectures tailored for complex graph networks with billions of nodes edges, while enhancing performance across diverse graph mining tasks such as recommendation systems, anomaly detection, and beyond. Ns incorporate long range or global aggregations to distinguish nodes in the graph. however, these aggregations usually require iteratively maintaining and updating full raph information, which limits their eficiency when applying to large scale graphs. in this paper, we propose sigma, an eficient global hete. [aaai 2025] "lightweight yet fine grained: a graph capsule convolutional network with subspace alignment for shared account sequential recommendation" c30. For mobility relationship inference integrating semantic features, this project proposes a friend relationship inference model based on graph embedding, which introduces semantics such as poi categories into meeting events, effectively improving the inference performance of friend relationship.
Sigma Ouc [aaai 2025] "lightweight yet fine grained: a graph capsule convolutional network with subspace alignment for shared account sequential recommendation" c30. For mobility relationship inference integrating semantic features, this project proposes a friend relationship inference model based on graph embedding, which introduces semantics such as poi categories into meeting events, effectively improving the inference performance of friend relationship. [2025 11 08] congratulations to xiang li as the first author for having the paper "multiplex heterogeneous graph neural networks with euclidean riemannian mutual space synergy" accepted by aaai 2026! 🎉🎉🎉. A highly customizable hugo research group theme powered by wowchemy website builder. My research focuses on graph neural networks, and i am still exploring more specific areas within this field. email: [email protected]. Based on this, we design an efficient and effective heterophily graph neural network, named sigma, to address heterophily graph learning problems, with theoretical guarantee and superior computation complexity.
Sigma Ouc [2025 11 08] congratulations to xiang li as the first author for having the paper "multiplex heterogeneous graph neural networks with euclidean riemannian mutual space synergy" accepted by aaai 2026! 🎉🎉🎉. A highly customizable hugo research group theme powered by wowchemy website builder. My research focuses on graph neural networks, and i am still exploring more specific areas within this field. email: [email protected]. Based on this, we design an efficient and effective heterophily graph neural network, named sigma, to address heterophily graph learning problems, with theoretical guarantee and superior computation complexity.
Comments are closed.