no code implementations • 14 May 2023 • Behnaz Soltani, Yipeng Zhou, Venus Haghighi, John C. S. Lui
In traditional machine learning, it is trivial to conduct model evaluation since all data samples are managed centrally by a server.
no code implementations • 13 Feb 2023 • Nasrin Shabani, Jia Wu, Amin Beheshti, Quan Z. Sheng, Jin Foo, Venus Haghighi, Ambreen Hanif, Maryam Shahabikargar
Hence, this paper presents a comprehensive survey of progress in deep learning summarization techniques that rely on graph neural networks (GNNs).
no code implementations • 8 Jul 2022 • Venus Haghighi, Behnaz Soltani, Adnan Mahmood, Quan Z. Sheng, Jian Yang
Anomaly detection in attributed networks has received a considerable attention in recent years due to its applications in a wide range of domains such as finance, network security, and medicine.
no code implementations • 8 Jul 2022 • Behnaz Soltani, Venus Haghighi, Adnan Mahmood, Quan Z. Sheng, Lina Yao
The main challenges of FL is that end devices usually possess various computation and communication capabilities and their training data are not independent and identically distributed (non-IID).