2 citations · 3 across the 4 of their papers we have counts for
4 papers
Origin-Destination Demand Prediction: An Urban Radiation and Attraction Perspective
Xuan Ma, Zepeng Bao, Ming Zhong +5
In recent years, origin-destination (OD) demand prediction has gained significant attention for its profound implications in urban development. Existing data-driven deep learning m…
Retrofitting Temporal Graph Neural Networks with Transformer
Qiang Huang, Xiao Yan, Xin Wang +5
Temporal graph neural networks (TGNNs) outperform regular GNNs by incorporating time information into graph-based operations. However, TGNNs adopt specialized models (e.g., TGN, TG…
PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory System
Steve Rhyner, Haocong Luo, Juan Gómez-Luna +6
Modern Machine Learning (ML) training on large-scale datasets is a very time-consuming workload. It relies on the optimization algorithm Stochastic Gradient Descent (SGD) due to it…
Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning
Yuxiang Wang, Xiao Yan, Chuang Hu +5
For graph self-supervised learning (GSSL), masked autoencoder (MAE) follows the generative paradigm and learns to reconstruct masked graph edges or node features. Contrastive Learn…