no code implementations • 23 Mar 2024 • Ryoma Sato
The problem is, that even if users are dissatisfied, they often do not have the means to resolve their dissatisfaction.
no code implementations • 7 Dec 2023 • Ryoma Sato
As a result, users are hesitant to utilize machine translation engines for data demanding high levels of privacy protection, thereby missing out on their benefits.
1 code implementation • 13 Oct 2023 • Ryoma Sato, Yuki Takezawa, Han Bao, Kenta Niwa, Makoto Yamada
LLMs can generate texts that cannot be distinguished from human-written texts.
no code implementations • 2 Oct 2023 • Yuki Takezawa, Ryoma Sato, Han Bao, Kenta Niwa, Makoto Yamada
Although existing watermarking methods have successfully detected texts generated by LLMs, they significantly degrade the quality of the generated texts.
1 code implementation • 26 Jan 2023 • Ryoma Sato
These results show that GNNs can fully exploit the graph structure by themselves, and in effect, GNNs can use both the hidden and explicit node features for downstream tasks.
1 code implementation • 15 Oct 2022 • Ryoma Sato
In this paper, we advocate that such a task-specific pool is not always available and propose the use of a myriad of unlabelled data on the Web for the pool for which active learning is applied.
no code implementations • 30 Sep 2022 • Yuki Takezawa, Han Bao, Kenta Niwa, Ryoma Sato, Makoto Yamada
In this study, we propose Momentum Tracking, which is a method with momentum whose convergence rate is proven to be independent of data heterogeneity.
1 code implementation • 21 Aug 2022 • Ryoma Sato
This approach opens the door to user-defined fair systems even if the official recommender system of the service is not fair.
1 code implementation • 21 Aug 2022 • Ryoma Sato, Makoto Yamada, Hisashi Kashima
The main difficulty in investigating the effects is that we need to know counterfactual results, which are not available in reality.
no code implementations • 24 Jun 2022 • Makoto Yamada, Yuki Takezawa, Ryoma Sato, Han Bao, Zornitsa Kozareva, Sujith Ravi
In this paper, we aim to approximate the 1-Wasserstein distance by the tree-Wasserstein distance (TWD), where TWD is a 1-Wasserstein distance with tree-based embedding and can be computed in linear time with respect to the number of nodes on a tree.
1 code implementation • 17 Jun 2022 • Ryoma Sato
In this framework, each user builds their own search system that meets their preference with a user-defined scoring function and user-defined interface.
1 code implementation • NAACL 2022 • Ryoma Sato
In this study, we propose WordTour, unsupervised one-dimensional word embeddings.
1 code implementation • 30 Dec 2021 • Ryoma Sato
We assume the user can access the database through a search query with tight API limits.
1 code implementation • 8 Sep 2021 • Yuki Takezawa, Ryoma Sato, Zornitsa Kozareva, Sujith Ravi, Makoto Yamada
By contrast, the Wasserstein distance on a tree, called the tree-Wasserstein distance, can be computed in linear time and allows for the fast comparison of a large number of distributions.
1 code implementation • 30 May 2021 • Ryoma Sato
This can be problematic because a group can be dissatisfied with the recommended package owing to some unobserved reasons, even if the score is high.
1 code implementation • 30 May 2021 • Ryoma Sato, Makoto Yamada, Hisashi Kashima
The original study on WMD reported that WMD outperforms classical baselines such as bag-of-words (BOW) and TF-IDF by significant margins in various datasets.
1 code implementation • 26 May 2021 • Ryoma Sato
The key challenge is that a user does not have access to the log data of other users or the latent representations of items.
no code implementations • 27 Jan 2021 • Yuki Takezawa, Ryoma Sato, Makoto Yamada
Specifically, we rewrite the Wasserstein distance on the tree metric by the parent-child relationships of a tree and formulate it as a continuous optimization problem using a contrastive loss.
no code implementations • 1 Jan 2021 • Mathis Petrovich, Chao Liang, Ryoma Sato, Yanbin Liu, Yao-Hung Hubert Tsai, Linchao Zhu, Yi Yang, Ruslan Salakhutdinov, Makoto Yamada
To show the effectiveness of FROT, we propose using the FROT algorithm for the layer selection problem in deep neural networks for semantic correspondence.
1 code implementation • 19 Oct 2020 • Ryoma Sato, Makoto Yamada, Hisashi Kashima
We use a bias correction method to estimate the potential impact of choosing a publication venue effectively and to recommend venues based on the potential impact of papers in each venue.
1 code implementation • NeurIPS 2020 • 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.
1 code implementation • 25 May 2020 • Mathis Petrovich, Chao Liang, Ryoma Sato, Yanbin Liu, Yao-Hung Hubert Tsai, Linchao Zhu, Yi Yang, Ruslan Salakhutdinov, Makoto Yamada
To show the effectiveness of FROT, we propose using the FROT algorithm for the layer selection problem in deep neural networks for semantic correspondence.
no code implementations • 9 Mar 2020 • Ryoma Sato
Graph neural networks (GNNs) are effective machine learning models for various graph learning problems.
1 code implementation • 8 Feb 2020 • Ryoma Sato, Makoto Yamada, Hisashi Kashima
Through experiments, we show that the addition of random features enables GNNs to solve various problems that normal GNNs, including the graph convolutional networks (GCNs) and graph isomorphism networks (GINs), cannot solve.
1 code implementation • 5 Feb 2020 • Ryoma Sato, Marco Cuturi, Makoto Yamada, Hisashi Kashima
Building on \cite{memoli-2011}, who proposed to represent each point in each distribution as the 1D distribution of its distances to all other points, we introduce in this paper the Anchor Energy (AE) and Anchor Wasserstein (AW) distances, which are respectively the energy and Wasserstein distances instantiated on such representations.
no code implementations • NeurIPS 2019 • Ryoma Sato, Makoto Yamada, Hisashi Kashima
We theoretically demonstrate that the most powerful GNN can learn approximation algorithms for the minimum dominating set problem and the minimum vertex cover problem with some approximation ratios with the aid of the theory of distributed local algorithms.
1 code implementation • 26 Feb 2019 • Ryoma Sato, Makoto Yamada, Hisashi Kashima
We propose HiSampler, the hard instance sampler, to model the hard instance distribution of graph algorithms.
no code implementations • 23 Jan 2019 • 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, and recommender systems.