83 citations · 160 across the 26 of their papers we have counts for
14 papers · 1 filter
Parameter-free Clipped Gradient Descent Meets Polyak
Yuki Takezawa, Han Bao, Ryoma Sato +2
Gradient descent and its variants are de facto standard algorithms for training machine learning models. As gradient descent is sensitive to its hyperparameters, we need to tune th…
Embarrassingly Simple Text Watermarks
Ryoma Sato, Yuki Takezawa, Han Bao +2
We propose Easymark, a family of embarrassingly simple yet effective watermarks. Text watermarking is becoming increasingly important with the advent of Large Language Models (LLM)…
Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence
Yuki Takezawa, Ryoma Sato, Han Bao +2
Decentralized learning has recently been attracting increasing attention for its applications in parallel computation and privacy preservation. Many recent studies stated that the…
Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure
Ryoma Sato
Graph Neural Networks (GNNs) are popular models for graph learning problems. GNNs show strong empirical performance in many practical tasks. However, the theoretical properties hav…
Active Learning from the Web
Ryoma Sato
Labeling data is one of the most costly processes in machine learning pipelines. Active learning is a standard approach to alleviating this problem. Pool-based active learning firs…
Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data
Yuki Takezawa, Han Bao, Kenta Niwa +2
SGD with momentum is one of the key components for improving the performance of neural networks. For decentralized learning, a straightforward approach using momentum is Distribute…
Re-evaluating Word Mover's Distance
Ryoma Sato, Makoto Yamada, Hisashi Kashima
The word mover's distance (WMD) is a fundamental technique for measuring the similarity of two documents. As the crux of WMD, it can take advantage of the underlying geometry of th…
Supervised Tree-Wasserstein Distance
Yuki Takezawa, Ryoma Sato, Makoto Yamada
To measure the similarity of documents, the Wasserstein distance is a powerful tool, but it requires a high computational cost. Recently, for fast computation of the Wasserstein di…
Fast Unbalanced Optimal Transport on a Tree
Ryoma Sato, Makoto Yamada, Hisashi Kashima
This study examines the time complexities of the unbalanced optimal transport problems from an algorithmic perspective for the first time. We reveal which problems in unbalanced op…
A Survey on The Expressive Power of Graph Neural Networks
Ryoma Sato
Graph neural networks (GNNs) are effective machine learning models for various graph learning problems. Despite their empirical successes, the theoretical limitations of GNNs have…
Random Features Strengthen Graph Neural Networks
Ryoma Sato, Makoto Yamada, Hisashi Kashima
Graph neural networks (GNNs) are powerful machine learning models for various graph learning tasks. Recently, the limitations of the expressive power of various GNN models have bee…
Approximation Ratios of Graph Neural Networks for Combinatorial Problems
Ryoma Sato, Makoto Yamada, Hisashi Kashima
In this paper, from a theoretical perspective, we study how powerful graph neural networks (GNNs) can be for learning approximation algorithms for combinatorial problems. To this e…
Learning to Sample Hard Instances for Graph Algorithms
Ryoma Sato, Makoto Yamada, Hisashi Kashima
Hard instances, which require a long time for a specific algorithm to solve, help (1) analyze the algorithm for accelerating it and (2) build a good benchmark for evaluating the pe…
Constant Time Graph Neural Networks
Ryoma Sato, Makoto Yamada, Hisashi Kashima
The recent advancements in graph neural networks (GNNs) have led to state-of-the-art performances in various applications, including chemo-informatics, question-answering systems,…