GNN Transformation Framework for Improving Efficiency and Scalability

1 code implementation • 25 Jul 2022 • Seiji Maekawa, Yuya Sasaki, George Fletcher, Makoto Onizuka

We propose a framework that automatically transforms non-scalable GNNs into precomputation-based GNNs which are efficient and scalable for large-scale graphs.

Retrieval Helps or Hurts? A Deeper Dive into the Efficacy of Retrieval Augmentation to Language Models

1 code implementation • 21 Feb 2024 • Seiji Maekawa, Hayate Iso, Sairam Gurajada, Nikita Bhutani

We demonstrate the efficacy of our finer-grained metric and insights through an adaptive retrieval system that selectively employs retrieval and recall based on the frequencies of entities and relations in the question.

Memorization Question Answering +1

Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs

1 code implementation • 18 Jun 2022 • Seiji Maekawa, Koki Noda, Yuya Sasaki, Makoto Onizuka

We hope this work offers interesting insights for future research.

Attribute Node Classification

Non-linear Attributed Graph Clustering by Symmetric NMF with PU Learning

1 code implementation • 21 Sep 2018 • Seiji Maekawa, Koh Takeuch, Makoto Onizuka

We consider the clustering problem of attributed graphs.

Attribute Clustering +1

A Simple and Scalable Graph Neural Network for Large Directed Graphs

1 code implementation • 14 Jun 2023 • Seiji Maekawa, Yuya Sasaki, Makoto Onizuka

In response, we propose a simple yet holistic classification method A2DUG which leverages all combinations of node representations in directed and undirected graphs.

Classification Node Classification