Toyotaro Suzumura
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Toyotaro Suzumura has a total of 108 co-authors. Here are the top co-authors by number of shared publications:
- Masatoshi Hanai
Information Technology Center, The University of Tokyo, Tokyo 113-0032, Japan
5 shared publications - Miyuru Dayarathna
WSO2, Inc 787 Castro Street 94041 Mountain View CA USA
3 shared publications - Sanath Jayasena
Dept of Computer Science & Engineering, University of Moratuwa
3 shared publications - Daisuke Kikuta
Rakuten Institute of Technology (RIT), Rakuten Group, Inc., Tokyo, Japan
2 shared publications Gayan Mettananda
Dept of Computer Science & Engineering, University of Moratuwa
2 shared publications- Hiroki Kanezashi
The University of Tokyo,Information Technology Center,Tokyo,Japan
2 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8946-8950
NewsReX: An Open-Source Multi-Framework for Neural News Recommendation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8946-8950
Open AccessNewsReX: An Open-Source Multi-Framework for Neural News Recommendation
- Open Access
- 1 January 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
Fast and accurate prediction of lattice thermal conductivity via machine learning surrogates
The appearance of generative models has opened vast chemical spaces in the design of functional materials.
- 1 January 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
Open AccessFast and accurate prediction of lattice thermal conductivity via machine learning surrogates
The appearance of generative models has opened vast chemical spaces in the design of functional materials.
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1238-1243
Enhancing Graph-Based Advanced Persistent Threat Detection with LLM Sentence Embedding
Advanced Persistent Threat (APT) attacks represent a sophisticated and growing danger to modern information systems. While provenance graphs are a promising tool for detecting these complex threats, their effectiveness is often limited by a failure to harness the rich semantic information contained within raw system logs. This paper proposes a novel detection framework that addresses this gap by leveraging a Large Language Model (LLM) to embed deep semantic meaning from system logs directly into the graph's features. Our approach enhances a state-of-the-art Graph Neural Network (GNN)-based method by replacing its simple embedding technique with an LLM-based sentence embedding method, specifically enriching the graph's edge features to capture deeper contextual information. Experimental results on the challenging Unicorn Wget dataset demonstrate the superiority of our method. It surpassed the baseline in all evaluation metrics, achieving an F1-Score of 96.12 % and an AUC of 98.52 %, compared to the baseline's 94.36 % F1-Score and 97.39% AUC. Furthermore, our method achieved a lower false positive rate of 6.68 %, indicating a more precise and reliable detection capability. These findings highlight the value of integrating semantic embeddings from LLMs to improve the detection of stealthy, complex cyberattacks.
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1238-1243
Enhancing Graph-Based Advanced Persistent Threat Detection with LLM Sentence Embedding
Advanced Persistent Threat (APT) attacks represent a sophisticated and growing danger to modern information systems. While provenance graphs are a promising tool for detecting these complex threats, their effectiveness is often limited by a failure to harness the rich semantic information contained within raw system logs. This paper proposes a novel detection framework that addresses this gap by leveraging a Large Language Model (LLM) to embed deep semantic meaning from system logs directly into the graph's features. Our approach enhances a state-of-the-art Graph Neural Network (GNN)-based method by replacing its simple embedding technique with an LLM-based sentence embedding method, specifically enriching the graph's edge features to capture deeper contextual information. Experimental results on the challenging Unicorn Wget dataset demonstrate the superiority of our method. It surpassed the baseline in all evaluation metrics, achieving an F1-Score of 96.12 % and an AUC of 98.52 %, compared to the baseline's 94.36 % F1-Score and 97.39% AUC. Furthermore, our method achieved a lower false positive rate of 6.68 %, indicating a more precise and reliable detection capability. These findings highlight the value of integrating semantic embeddings from LLMs to improve the detection of stealthy, complex cyberattacks.
- Open Access
From Votes to Volatility Predicting the Stock Market on Election Day
Stock market forecasting has been a topic of extensive research, aiming to provide investors with optimal stock recommendations for higher returns. In recent years, this field has gained even more attention due to the widespread adoption of deep learning models. While these models have achieved impressive accuracy in predicting stock behavior, tailoring them to specific scenarios has become increasingly important. Election Day represents one such critical scenario, characterized by intensified market volatility, as the winning candidate's policies significantly impact various economic sectors and companies. To address this challenge, we propose the Election Day Stock Market Forecasting (EDSMF) Model. Our approach leverages the contextual capabilities of large language models alongside specialized agents designed to analyze the political and economic consequences of elections. By building on a state-of-the-art architecture, we demonstrate that EDSMF improves the predictive performance of the S&P 500 during this uniquely volatile day.
Open AccessFrom Votes to Volatility Predicting the Stock Market on Election Day
Stock market forecasting has been a topic of extensive research, aiming to provide investors with optimal stock recommendations for higher returns. In recent years, this field has gained even more attention due to the widespread adoption of deep learning models. While these models have achieved impressive accuracy in predicting stock behavior, tailoring them to specific scenarios has become increasingly important. Election Day represents one such critical scenario, characterized by intensified market volatility, as the winning candidate's policies significantly impact various economic sectors and companies. To address this challenge, we propose the Election Day Stock Market Forecasting (EDSMF) Model. Our approach leverages the contextual capabilities of large language models alongside specialized agents designed to analyze the political and economic consequences of elections. By building on a state-of-the-art architecture, we demonstrate that EDSMF improves the predictive performance of the S&P 500 during this uniquely volatile day.
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2970-2975
Graph-Based Audience Expansion Model for Marketing Campaigns
Audience Expansion, a technique for identifying new audiences with similar behaviors to the original target or seed users. The major challenges include a heterogeneous user base, intricate marketing campaigns, constraints imposed by sparsity, and limited seed users, which lead to overfitting. In this context, we propose a novel solution named AudienceLinkNet, specifically designed to address the challenges associated with audience expansion in the context of Rakuten's diverse services and its clients. Our approach formulates the audience expansion problem as a graph problem and explores the combination of a Pre-trained Knowledge Graph Embedding Model and a Graph Convolutional Networks (GCNs). It emphasizes the structural retention properties of GCNs, enabling the model to overcome challenges related to cross-service data usage, sparsity and limited seed data. AudienceLinkNet simplifies the targeting process for small and large marketing campaigns and better utilizes demographics and behavioral attributes for targeting. Extensive experiments on our advertising platform, Rakuten AIris Target Prospecting, demonstrate the effectiveness of our audience expansion model. Additionally, we present the limitations of AudienceLinkNet.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 2970-2975
Open AccessGraph-Based Audience Expansion Model for Marketing Campaigns
Audience Expansion, a technique for identifying new audiences with similar behaviors to the original target or seed users. The major challenges include a heterogeneous user base, intricate marketing campaigns, constraints imposed by sparsity, and limited seed users, which lead to overfitting. In this context, we propose a novel solution named AudienceLinkNet, specifically designed to address the challenges associated with audience expansion in the context of Rakuten's diverse services and its clients. Our approach formulates the audience expansion problem as a graph problem and explores the combination of a Pre-trained Knowledge Graph Embedding Model and a Graph Convolutional Networks (GCNs). It emphasizes the structural retention properties of GCNs, enabling the model to overcome challenges related to cross-service data usage, sparsity and limited seed data. AudienceLinkNet simplifies the targeting process for small and large marketing campaigns and better utilizes demographics and behavioral attributes for targeting. Extensive experiments on our advertising platform, Rakuten AIris Target Prospecting, demonstrate the effectiveness of our audience expansion model. Additionally, we present the limitations of AudienceLinkNet.
- Open Access
- 4 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Cloud Data Acquisition from Shared-Use Facilities in A University-Scale Laboratory Information Management System
Effective data management across large-scale shared-use materials-science facility centers is crucial, as high-end facilities available at such centers are indispensable for cutting-edge research in modern materials science. However, establishing network connectivity for these facilities is often not practically feasible due to its uniqueness, forcing users to resort to the traditional manual method of data acquisition and transfer, such as the use of DVD disks. In this paper, we introduce an IoT device designed to facilitate direct data transfer from these non-networked and shared-use facilities to a cloud system. We propose a novel data transfer algorithm that integrates user management with data transfer processes for safely assigning each user's data to its private storage space on the cloud. The proposed technology serves as a fundamental building block in shaping a smarter laboratory information management system for the advancement of material researches and developments.
- 4 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessCloud Data Acquisition from Shared-Use Facilities in A University-Scale Laboratory Information Management System
Effective data management across large-scale shared-use materials-science facility centers is crucial, as high-end facilities available at such centers are indispensable for cutting-edge research in modern materials science. However, establishing network connectivity for these facilities is often not practically feasible due to its uniqueness, forcing users to resort to the traditional manual method of data acquisition and transfer, such as the use of DVD disks. In this paper, we introduce an IoT device designed to facilitate direct data transfer from these non-networked and shared-use facilities to a cloud system. We propose a novel data transfer algorithm that integrates user management with data transfer processes for safely assigning each user's data to its private storage space on the cloud. The proposed technology serves as a fundamental building block in shaping a smarter laboratory information management system for the advancement of material researches and developments.
- Open Access
- 13 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation
- 13 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessRevisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation
- Open Access
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 24-34
✨ Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations
Precisely recommending candidate news articles to users has always been a core challenge for personalized news recommendation systems. Most recent works primarily focus on using advanced natural language processing techniques to extract semantic information from rich textual data, employing content-based methods derived from local historical news. However, this approach lacks a global perspective, failing to account for users’ hidden motivations and behaviors beyond semantic information. To address this challenge, we propose a novel model called GLORY (Global-LOcal news Recommendation sYstem), which combines global representations learned from other users with local representations to enhance personalized recommendation systems. We accomplish this by constructing a Global-aware Historical News Encoder, which includes a global news graph and employs gated graph neural networks to enrich news representations, thereby fusing historical news representations by a historical news aggregator. Similarly, we extend this approach to a Global Candidate News Encoder, utilizing a global entity graph and a candidate news aggregator to enhance candidate news representation. Evaluation results on two public news datasets demonstrate that our method outperforms existing approaches. Furthermore, our model offers more diverse recommendations1.
- 14 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 24-34
Open Access✨ Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations
Precisely recommending candidate news articles to users has always been a core challenge for personalized news recommendation systems. Most recent works primarily focus on using advanced natural language processing techniques to extract semantic information from rich textual data, employing content-based methods derived from local historical news. However, this approach lacks a global perspective, failing to account for users’ hidden motivations and behaviors beyond semantic information. To address this challenge, we propose a novel model called GLORY (Global-LOcal news Recommendation sYstem), which combines global representations learned from other users with local representations to enhance personalized recommendation systems. We accomplish this by constructing a Global-aware Historical News Encoder, which includes a global news graph and employs gated graph neural networks to enrich news representations, thereby fusing historical news representations by a historical news aggregator. Similarly, we extend this approach to a Global Candidate News Encoder, utilizing a global entity graph and a candidate news aggregator to enhance candidate news representation. Evaluation results on two public news datasets demonstrate that our method outperforms existing approaches. Furthermore, our model offers more diverse recommendations1.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 3400-3404
Exploring 360-Degree View of Customers for Lookalike Modeling
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 3400-3404
Open AccessExploring 360-Degree View of Customers for Lookalike Modeling