3 papers
cs.LG2025
A Proportional-Integral Controller-Incorporated SGD Algorithm for High Efficient Latent Factor Analysis
Jinli Li, Shiyu Long, Minglian Han
In industrial big data scenarios, high-dimensional sparse matrices (HDI) are widely used to characterize high-order interaction relationships among massive nodes. The stochastic gr…
cs.LG2025
High-order Graph Neural Networks with Common Neighbor Awareness for Link Prediction
Ling Wang, Minglian Han
Link prediction is a fundamental task in dynamic graph learning (DGL), inherently shaped by the topology of the DG. Recent advancements in dynamic graph neural networks (DGNN), pri…
cs.LG2025
Learning Dynamic Graphs via Tensorized and Lightweight Graph Convolutional Networks
Minglian Han
A dynamic graph (DG) is frequently encountered in numerous real-world scenarios. Consequently, A dynamic graph convolutional network (DGCN) has been successfully applied to perform…