自己紹介
私は大阪大学の博士後期課程1年目の学生であり,
産業科学研究所(SANKEN)にて特任研究員を務めています.
現在は同研究所にて,櫻井保志教授および松原靖子教授にご指導を受けています.
研究テーマは主に,ベイズによるイベントテンソル分解 [C1]に取り組んでいます.
学士号および修士号は,櫻井保志教授のご指導のもと,それぞれ 2024 年3月および2026 年 3 月に取得いたしました.
履歴書は こちらでダウンロードできます.
学歴
-
高等学校
- 普通科
- 兵庫県立八鹿高等学校
- 日本,兵庫県
-
–
-
学士(工学)
- 工学部電子情報工学科
- 大阪大学
- 日本,大阪府
-
–
-
修士(情報科学)
- 情報科学研究科情報システム工学専攻
- 大阪大学
- 日本,大阪府
-
–
-
博士(情報科学)
- 情報科学研究科情報システム工学専攻
- 大阪大学
- 日本,大阪府
-
–
職歴
- デジタル技術エンジニア
- 日本,大阪府
-
– - 特任研究員
- 日本,大阪府
-
–
Crev
産業科学研究所(SANKEN)
研究業績
-
[C1] Multi-Aspect Mining and Anomaly Detection for Heterogeneous Tensor Streams
- 著者
Soshi Kakio , Yasuko Matsubara , Ren Fujiwara , Yasushi Sakurai - 会議
- The ACM Web Conference 2026 (WWW '26)
- 採択率
- 20.1% (676/3370)
- リンク
- キーワード
- bayesiananomaly detectiongaussian process
- 序文
-
詳細 Analysis and anomaly detection in event tensor streams consisting of timestamps and multiple attributes —such as communication logs(time, IP address, packet length)—are essential tasks in data mining. While existing tensor decomposition and anomaly detection methods provide useful insights, they face the following two limitations. (i) They cannot handle heterogeneous tensor streams, which comprises both categorical attributes(e.g., IP address) and continuous attributes(e.g., packet length).They typically require either discretizing continuous attributes or treating categorical attributes as continuous, both of which distort the underlying statistical properties of the data.Furthermore, incorrect assumptions about the distribution family of continuous attributes often degrade the model’s performance. (ii) They discretize timestamps, failing to track the temporal dynamics of streams(e.g., trends, abnormal events), which makes them ineffective for detecting anomalies at the group level, referred to as 'group anomalies' (e.g, DoS attacks). To address these challenges, we propose HeteroComp, a method for continuously summarizing heterogeneous tensor streams into 'components' representing latent groups in each attribute and their temporal dynamics, and detecting group anomalies. Our method employs Gaussian process priors to model unknown distributions of continuous attributes, and temporal dynamics, which directly estimate probability densities from data.Extracted components give concise but effective summarization, enabling accurate group anomaly detection. Extensive experiments on real datasets demonstrate that HeteroComp outperforms the state-of-the-art algorithms for group anomaly detection accuracy, and its computational time does not depend on the data stream length.
- 概要図
