7 citations · 24 across the 23 of their papers we have counts for
7 papers · 1 filter
Path association rule mining
Yuya Sasaki
Graph association rule mining is a data mining technique used for discovering regularities in graph data. In this study, we propose a novel concept, {\it path association rule mini…
GNN Transformation Framework for Improving Efficiency and Scalability
Seiji Maekawa, Yuya Sasaki, George Fletcher +1
We propose a framework that automatically transforms non-scalable GNNs into precomputation-based GNNs which are efficient and scalable for large-scale graphs. The advantages of our…
Scaling Private Deep Learning with Low-Rank and Sparse Gradients
Ryuichi Ito, Seng Pei Liew, Tsubasa Takahashi +2
Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the m…
An Empirical Study of Personalized Federated Learning
Koji Matsuda, Yuya Sasaki, Chuan Xiao +1
Federated learning is a distributed machine learning approach in which a single server and multiple clients collaboratively build machine learning models without sharing datasets o…
Predicting Parking Lot Availability by Graph-to-Sequence Model: A Case Study with SmartSantander
Yuya Sasaki, Junya Takayama, Juan Ramón Santana +3
Nowadays, so as to improve services and urban areas livability, multiple smart city initiatives are being carried out throughout the world. SmartSantander is a smart city project i…
Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs
Seiji Maekawa, Koki Noda, Yuya Sasaki +1
Graph Neural Networks (GNNs) have achieved great success on a node classification task. Despite the broad interest in developing and evaluating GNNs, they have been assessed with l…
Similarity Search on Computational Notebooks
Misato Horiuchi, Yuya Sasaki, Chuan Xiao +1
Computational notebook software such as Jupyter Notebook is popular for data science tasks. Numerous computational notebooks are available on the Web and reusable; however, searchi…