Murata Laboratory is doing research on artificial intelligence, especially network science, machine learning and Web mining.


News

Admission:
If you want to apply for Tokyo Tech IGP(C), please read this site, and send the following documents to Murata by email: (i) your CV, (ii) your grade transcript(s), (iii) research proposal, (iv) list of publications, and (v) your thesis for graduating master/undergraduate course (if it is not written in English, please send any English technical papers/documents written by you). We will think about the possibilities of accepting you based on these documents. We will accept extraordinary excellent applicants only.

There will be a briefing of the entrance exam of our graduate school and open laboratory on April 20(Sat). If you want to join, please register in advance.
https://www.titech.ac.jp/0/prospective-students/news/2024/068740(written in Japanese)
Detailed information on this day is shown in the following site (written in Japanese).
https://www.li.c.titech.ac.jp/admission/2024-1.html
Information about the briefing of other dates is availabe in the following site (written in Japanese).
https://www.titech.ac.jp/0/prospective-students/open-campus/briefing/department-cs
Announcements from the Department of Computer Science are as follows (written in Japanese).
https://educ.titech.ac.jp/cs/eng/
"Graduate School Admissions FAQ" is in the following site.
https://www.titech.ac.jp/english/admissions/prospective-students/admissions/faq
Application Guideline of Tokyo Tech Graduate School (for last year) is available online (for the applicants of master course)(written in Japanese). Doctor course applicants have to request printed version of the guideline.
https://www.titech.ac.jp/admissions/prospective-students/admissions/guide
As mentioned in the guideline, please check the following "Admission Update" frequently. The guideline may subject to change because of COVID-19.
https://www.titech.ac.jp/english/entrance_information/
Master course applicants who wish to join Murata laboratory do not have to send emails in advance. (except Tokyo Tech IGP(C) applicants)
Doctor course applicants who wish to join Murata laboratory have to send the following documents by email in advance: (i) your CV, (ii) your grade transcript(s), (iii) research proposal, (iv) list of publications, and (v) your thesis for graduating master/undergraduate course (if it is not written in English, please send any English technical papers/documents written by you).
Master / doctor course applicants who still have no English proficiency test score are strongly requested to take TOEIC or TOEFL as soon as possible. (2024.3.18)

A paper (Title:"DEGNN: Dual Experts Graph Neural Network Handling Both Edge and Node Feature Noise") written by Mr. Tai Hasegawa (second grade of master course student) is accepted by PAKDD 2024. (2024.1.29)

Murata gave a lecture titled "Machine Learning for Structural Data with Graph Neural Networks" at AIST AI seminar (in Japanese) (slides available in AIST site). (2023.10.17)

A paper (Title:"Predicting Potential Real-time Donations in YouTube Live Streaming Services via Continuous-time Dynamic Graph") written by Mr. Jin Ruidong (3rd grade of doctoral student) is accepted by Machine Learning. (2023.10.10)

A paper (Title:"Class-Incremental Learning using Diffusion Model for Distillation and Replay") written by Mr. Quentin Jodelet (3rd grade of doctoral student) won the Best Paper Award in 1st Workshop on Visual Continual Learning. (2023.10.2)

A paper (Title:"Link prediction for ex ante influence maximization on temporal networks") written by Mr. Eric Yanchenko (North Carolina State University, JSPS Researcher in 2023), Murata and Prof. Petter Holme (Aalto University) is accepted by Applied Network Science. (2023.9.14)

Admission:
Application period for International Grauduate Program (C) (IGP(C)) has started. If you are interested in our laboratory and want to apply for Tokyo Tech IGP(C) program to be a master/doctor student, please read this site carefully, and send necessary documents to Murata by email. Application deadline for April 2024 admission is October 15, 2023. (2023.9.2)

We explained our lab activities at Open Campus 2023 for high school students (in Japanese) (slides in Japanese). (2023.8.10)

A paper written by Dr. Sunil Kumar Maurya (title:"Feature Selection: Key to Enhance Node Classification with Graph Neural Networks") is selected as a cover story of CAAI Transactions on Intelligence Technology (photo). (2023.4.6)

A pamphlet of our lab is available (English version and Japanese version). (2023.1.11)

A paper (Title:"Strengthening Robustness under Adversarial Attacks using Brain Visual Codes") written by Ms. Zarina Rakhimberdina (3rd grade of doctoral student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted by IEEE Access (impact factor : 3.476). (2022.9.5)

A paper (Title:"Not All Neighbors are Friendly: Learning to Choose Hop Features to Improve Node Classification") written by Mr. Sunil Kumar Maurya (third grade of doctoral course student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted as a short paper of CIKM 2022. (2022.8.2)

Murata published a book titled "Graph Neural Networks: implementation with PyTorch" (Ohmsha (publisher) / Amazon / additional information). (2022.7.20)

A paper (Title:"Leaping Through Time with Gradient-based Adaptation for Recommendation") written by Mr. Nuttapong Chairatanakul (3rd grade of doctoral students), Dr. Liu Xin (AIRC, AIST) and Murata is accepted by AAAI 2022. (2021.12.1)

A paper (Title:"CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions") written by Mr. Quentin Jodelet (2nd grade of doctoral student) is accepted by Artificial Intelligence. (2021.11.26)

A paper (Title:"Natural Image Reconstruction from fMRI using Deep Learning: A Survey") written by Ms. Zarina Rakhimberdina (3rd grade of doctoral student), Mr. Quentin Jodelet (2nd grade of doctoral student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted by Frontiers in Neuroscience, section Brain Imaging Methods. (2021.11.24)

Murata gave a talk as an invited speaker of International Conference on Data Science and Official Statistics (ICDSOS 2021). (slides) (2021.11.13)

Murata gave an online lecture to the students of Maebashi High School in Gunma Prefecture (Title: "Understanding friendship and infectious disease spread in networks"). (slides) (2021.11.9)

Graduate School Admissions FAQ is available in the following site.
https://www.titech.ac.jp/english/graduate_school/admissions/faq.html
Murata gave a talk as an invited speaker of FAN 2021 Online (Title: "Graph Neural Networks"). (slides) (2021.9.21)

A paper (Title:"Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph") written by Mr. Nuttapong Chairatanakul (3rd grade of doctoral student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted by EMNLP 2021 as Findings of EMNLP. (2021.8.26)

Murata delivered an online lecture for study of university departments at Toshin preparatory school. (2021.8.7)

A paper (Title: "PGRA: Projected Graph Relation-Feature Attention Network for Heterogeneous Information Network Embedding") written by Mr. Nuttapong Chairatanakul (3rd grade of doctoral student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted by Information Sciences (impact factor : 5.910). (2021.4.21)

Murata and other 16 professors have received Education Award of Tokyo Tech (2019) for the implementation of Progressive Graduate Minor in Data Science and Artificial Intelligence. (2021.3.2)

Murata's dialogue at Mirai Dining appeared in TechTech, Tokyo Tech PR magazine (written in Japanese). It also appeared in Prospective Students of Tokyo Tech Web site. (2021.1.6)

A paper (Title: "Predicting Emergency Medical Service Demand with Bipartite Graph Convolutional Networks") written by Mr. Ruidong Jin (1st grade of doctoral student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted by IEEE Access (impact factor : 3.745). (2021.1.5)

Murata gave a lightening talk (Title:"Network Analysis and Visualization by Google Colaboratory") at Data Visualization meetup 2020. (slides) (2020.12.28)

A paper (Title:"Graph Neural Networks for Fast Node Ranking Approximation") written by Mr. Sunil Kumar Maurya (second grade of doctoral course student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted by ACM Transactions on Knowledge Discovery from Data (impact factor : 3.290). (2020.12.27)

A paper (Title: "Graph convolutional networks for graphs containing missing features") written by Mr. Hibiki Taguchi (2nd grade of master student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted by Future Generation Computer Systems (impact factor : 6.125). (2020.12.5)

Murata gave a talk as an invited speaker of WCTP 2020 (Title:"Networks, Deep Learning (and COVID-19)"). (slides) (2020.11.21)

Murata gave a talk in Educational Innovation Symposium 2020 (Title:"An Attempt of On-Demand Classes by T2SCHOLA") slides and videos (available inside of Tokyo Tech) (2020.11.13)

A paper (Title:"Active Learning on Graphs via Meta Learning") written by Mr. Kaushalya Madhawa (fourth grade of doctoral student) is accepted by ACML 2020 (acceptance rate:31%). (2020.8.26)

Murata wrote two Japanese articles ("COVID-19 and Networks" and "Web Intelligence" (co-authored with Prof. Yasufumi Takama)) to JSAI Journal Vol.35, No.5 (Sep. 2020) (2020.9.2)

Mr. Quentin Jodelet (a doctoral student of our laboratory) was in the top 4 challenge winners (among 79 teams) of CVPR Challenge on Continual Learning on June 14.(2020.6.15)

Our work appear in attempts for AI research for COVID-19 of AI Japan R&D Network: accurate decision of emergency transport hospitals using graph deep learning and centrality of temporal networks for preventing the spread of infection (in Japanese) (2020.6.1)

Ohmsha decided to print some more copies of the book ("Learning Network Analysis with Python" (in Japanese)) written by Murata. (2020.2.21)

Murata gave a talk as an invited speaker of MARAMI 2019 (title : Deep Learning Approaches for Networks (slides)). (2019.11.7)

Murata gave a talk as an invited speaker of a meeting of Plasma Electronics at Tohoku University. (slides (in Japanese)). (2019.9.25)

Murata published a book "Learning Network Analysis with Python" (bibliographic info & program codes / Ohmsha (publisher) / Amazon). (2019.9.15)

A paper (Title:"Recurrent Translation-based Network for Top-N Sparse Sequential Recommendation") written by Mr. Nuttapong Chairatanakul (first grade of doctoral course student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted by IEEE Access (impact factor : 4.098). (2019.8.22)

A paper (Title:"Fast Approximations of Betweenness Centrality using Graph Neural Networks") written by Mr. Sunil Kumar Maurya (first grade of doctoral course student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted as a short paper of CIKM 2019 (acceptance rate:21%). (2019.8.9)

Mr. Hibiki Taguchi receives JSAI Annual Conference Award (Oral Presentation) for his presentation (title: "Community detection in bipartite networks by multi label propagation algorithm") at The 33rd Annual Conference of the Japanese Society for Artificial Intelligence, 2019. (2019.8.1)

Mr. Makoto Tachibana received JSAI Incentive Award for his presentation (title: "Semi-supervised learning on network using structure features and graph convolution" (in Japanese)) at the 115th SIG meeting on Knowledge Base Systems. (2019.6.27)

Murata gave a talk (title: "Deep Learning Approaches for Eruption Prediction of Sakurajima") as an invited speaker of "Potentiality of Machine Learning in Solid Earth Sciences" session of JpGU Meeting 2019. (2019.5.26)

Murata gave a lecture on "Introduction of network analysis with Google Colaboratory" as one of the AI tool introduction of JSAI (codes and slides here). (2019.5.23)

Murata gave a talk (title: "Deep Learning Approaches for Eruption Prediction of Sakurajima") as an invited speaker of 115th SIG-KBS meeting of JSAI. (2018.11.23)

Mr. Hiep Le's work of the prediction of volcanic eruption of Sakurajima appeared in an article of monthly magazine Fole (in Japanese) issued by Mizuho Research Institute in October 2018. (2018.9.27)

A paper (Title:"Learning Community Structure with Variational Autoencoder") written by Mr. Choong Jun Jin (second grade of doctoral course student), Dr. Liu Xin (AIRC, AIST) and Murata is accepted as a full paper of IEEE ICDM 2018 (acceptance rate:8.86%). (2018.8.20)

Murata taught an intensive lecture on Complex Networks at Shanghai University of Finance and Economics. (2018.7.12-17)

Mr. Hiep Le's paper (Title: "Deep Modular Multimodal Fusion on Multiple Sensors for Volcano Activity Recognition") has been accepted by ECML-PKDD 2018 (acceptance rate:27%). (2018.6.19)

Mr. Hiep Le's research on predicting volcanic eruptions of Sakurajima (presented at JSAI 2018 on June 6, 2018) appeared in a local TV news of NHK Kagoshima and in an atricle of South Japan Newspaper (2018.6.7)
"Kagoshima NEWS WEB -- AI predicts eruptions of Sakurajima" (NHK Kagoshima, in Japanese)
"AI predicts eruptions of Sakurajima --- 51.9% accuracy achieved with four-stage warning system by research team of Tokyo Tech & Kyoto Univ." (South Japan Newspaper Company, in Japanese)

An article about Mr. Hiep Le's work on Sakurajima volcanic activity recognition appeared in Nikkei Newspaper (page 9) on Jan. 15, 2018. (2018.1.15)
"Tokyo Tech & Kyoto Univ. use AI for volcano activity recognition (Nikkei Newspaper (written in Japanese))" "Deep Learning Approach for Volcano Activity Recognition (News of the Dept. of CS (written in Japanese))" "Deep Learning Approach for Volcano Activity Recognition (link to an article of KBS meeting in Nov. 2017(written in Japanese))"

call for postdocs: Our laboratory takes part in RWBC-OIL(AIST-Tokyo Tech Real World Big-Data Computation Open Innovation Laboratory).
RWBC-OIL is a joint laboratory of Tokyo Tech and AIST for the analysis of real-world big data started from Feb. 2017 (news from Tokyo Tech (in Japanese), news from AIST (in Japanese)).
RWBC-OIL hires researchers of machine learning / deep learning / graph mining / high performance computing. Please read call for postdocs (in Japanese) for more information. If you are interested in, please contact Murata. (2017.4.6)


Mr. Yohei Oonuki receives JSAI Incentive Award for his presentation (title: "Prediction of relations among RDF entities by DNN" (in Japanese)) at the 41st SIG meeting on Semantic Web and Ontology. (2017.5.8)

Mr. Shun Nukui received JSAI Annual Conference Student Incentive Award for his presentation (title: "Constrained community detection based on semi-supervised non-negative matrix factorization on TensorFlow" (in Japanese)) at 2016 JSAI Annual Conference. (2017.3.1)

Murata was invited to MARAMI 2016 as an invited speaker, but the talk was canceled. (2016.10.14)

Murata gave a talk ("Mining and learning on heterogeneous networks") as an invited speaker at WIMS 2016 (slides). (2016.6.15)

Dr. Xin Liu and Mr. Weichu Liu's paper (title: "Community Detection in Multi-Partite Multi-Relational Networks Based on Information Compression") was accepted by New Generation Computing. (2016.3.7)

Mr. Phiradet Bangcharoensap's paper (title: "Transductive Classification on Heterogeneous Information Networks with Edge Betweenness-based Normalization") was accepted by WSDM 2016 conference (acceptance rate: 18.2%). (2015.10.14)

Mr. Phiradet Bangcharoensap's paper (title: "Two step graph-based semi-supervised learning for online auction fraud detection") was accepted by ECML-PKDD 2015 conference (acceptance rate: 28.6%). (2015.6.3)

Mr. Keisuke Nakata presented his work at CompleNet 2015(the 6th Workshop on Complex Networks). His photo is here. (2015.3.25)

Mr. Keisuke Nakata (title: "Speeding-up of Constrained Community Detection and Development of its Interactive Environment") received JSAI Annual Conference Award. 19 papers were selected out of 584 papers. (2014.7.22)

Dr. Xin Liu and Mr. Weichu Liu's paper (A Framework for Community Detection in Heterogeneous Multi-Relational Networks) was accepted by Advances in Complex Systems.(2014.7.9)

Dr. Xin Liu's paper (Detecting network communities beyond assortativity-related attributes) was accepted by Physical Review E.(2014.6.19)

Mr. Ikematsu's programs for detecting communities from n-partite networks are available online.
Reference:"Improvement of a Tripartite Modularity and Its Optimization Method"(written in Japanese)
(Transactions of the Japanese Society for Artificial Intelligence, Vol.29, No.2, pp.245-258, 2014)(2014.2.20)


Links

Another Web site of Murata laboratory

Department of Computer Science, School of Computing
Tokyo Institute of Technology