activity
20122023
most citedMR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions

120 citations · 262 across the 34 of their papers we have counts for

collaborators

34 papers

cs.CL2023★ 2 cited

ArcGPT: A Large Language Model Tailored for Real-world Archival Applications

Shitou Zhang, Jingrui Hou, Siyuan Peng +3

Archives play a crucial role in preserving information and knowledge, and the exponential growth of such data necessitates efficient and automated tools for managing and utilizing…

cs.LG2023★ 1 cited

Multiobjective Hydropower Reservoir Operation Optimization with Transformer-Based Deep Reinforcement Learning

Rixin Wu, Ran Wang, Jie Hao +2

Due to shortage of water resources and increasing water demands, the joint operation of multireservoir systems for balancing power generation, ecological protection, and the reside…

physics.hist-ph2023

Practicing carpe diem in the journey of studying physics: A brief review of the scientific contribution of Ru-Keng Su

Shaoyu Yin, Wei-Liang Qian, Ping Wang +2

We briefly review the scientific contributions of the late Prof. Ru-Keng Su in his academic life. In the area of intermediate and high-energy nuclear physics, Su explored various t…

cs.LG2023

Fast Gumbel-Max Sketch and its Applications

Yuanming Zhang, Pinghui Wang, Yiyan Qi +4

The well-known Gumbel-Max Trick for sampling elements from a categorical distribution (or more generally a non-negative vector) and its variants have been widely used in areas such…

cs.CR2023★ 1 cited

An Effective and Differentially Private Protocol for Secure Distributed Cardinality Estimation

Pinghui Wang, Chengjin Yang, Dongdong Xie +4

Counting the number of distinct elements distributed over multiple data holders is a fundamental problem with many real-world applications ranging from crowd counting to network mo…

cs.LG2023

Federated Learning over Coupled Graphs

Runze Lei, Pinghui Wang, Junzhou Zhao +6

Graphs are widely used to represent the relations among entities. When one owns the complete data, an entire graph can be easily built, therefore performing analysis on the graph i…