About Me

Research Associate @ Megagon Labs, California, USA
Ph.D. (Information Science)

email: seiji [at] megagon.ai
[github] [scholar] [LinkedIn]

Research Interests

• Natural Language Processing
  • Active Learning
  • Low-budget Training
• Graph Processing
  • Graph Neural Networks
  • Synthetic Graph Generation
  • Attributed Graph Clustering
• Social Network Analysis
• Follower Prediction
• Graph Analysis on Incomplete Networks
• Graph Database
  • Language-aware Indexing
  • Query Language

Experiences

• Research Associate:
  Megagon Labs Inc.
  2023-04 ~ present @ Mountain View, CA, USA
  
• Research Intern:
  Megagon Labs Inc.
  2022-01 ~ 2022-04 @ Mountain View, CA, USA
  Low-budget active learning. Aiming to reduce labeling costs (i.e., human effort) by focusing on informative data samples to train language models.
  Blog post in the company's HP
• Research Intern:
  Hotto Link Inc. - 株式会社ホットリンク
  2020-09 ~ 2020-10 @ Remote
  Follower prediction problem under the restriction of the small number of API calls.
  This work was press-released on the company's HP!
• Specially Appointed Researcher/Fellow (Part time) - 特任研究員S（非常勤）:
  Osaka University
  2020-04 ~ 2023-03
• Sales Enginner (Full-time) - 正社員:
  NTT DOCOMO, INC. - 株式会社NTTドコモ ソリューションサービス部
  2019-04 ~ 2020-03
• Study Abroad:
  Guest Researcher
  Eindhoven University of Technology (Technische Universiteit Eindhoven), Eindhoven, Netherlands
  2018-10 ~ 2018-12
• Study Abroad:
  Exchange Student
  The Chinese University of Hong Kong, Hong Kong
  2017-09 (30 days)

Publications

Preprint

1. Why Using Either Aggregated Features or Adjacency Lists in Directed or Undirected Graph? Empirical Study and Simple Classification Method. [paper] [code]
   Seiji Maekawa, Yuya Sasaki, Makoto Onizuka.
   in arXiv preprint, June 2023.

International Conferences/Workshops

1. Low-resource Interactive Active Labeling for Fine-tuning Language Models. [paper] [code]
   Seiji Maekawa, Dan Zhang, Hannah Kim, Sajjadur Rahman and Estevam Hruschka.
   in Findings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP), acceptance rate: 36% (=1168/3242), December 2022.
2. Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs. [paper] [code]
   Seiji Maekawa, Koki Noda, Yuya Sasaki, Makoto Onizuka.
   in Proceedings of the NeurIPS Datasets and Benchmarks Track, acceptance rate: 36% (=163/447), November 2022.
3. GNN Transformation Framework for Improving Efficiency and Scalability. [paper] [code]
   Seiji Maekawa, Yuya Sasaki, George Fletcher, Makoto Onizuka.
   in Proceedings of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), acceptance rate: 26%, Sep. 2022.
4. Benchmarking GNNs with GenCAT Workbench. [paper] [code] [demo video]
   Seiji Maekawa, Yuya Sasaki, George Fletcher, Makoto Onizuka.
   in Demo track of ECML/PKDD, Sep. 2022.
5. Effective Candidate Selection and Interpretable Interest Extraction for Follower Prediction on Social Media. [paper]
   Seiji Maekawa, Santi Saeyor, Takeshi Sakaki, Makoto Onizuka,
   in Proceedings of IEEE/WIC/ACM International Conference on Web Intelligence (WI-IAT), December 2021.
6. Adaptive Node Embedding Propagation for Semi-Supervised Classification. [paper]
   Yuya Ogawa, Seiji Maekawa, Yuya Sasaki, Yasuhiro Fujiwara, Makoto Onizuka.
   in Proceedings of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), Sep. 2021.
7. Controlling Internal Structure of Communities on Graph Generator. [paper]
   Hiroto Yamaguchi, Yuya Ogawa, Seiji Maekawa, Yuya Sasaki, Makoto Onizuka.
   in Proceedings of 2020 IEEE/ACM ASONAM Demos and Exhibitions Track, Vol.1, pp.937-940, Dec. 2020.
8. General Generator for Attributed Graphs with Community Structure. [paper] [code]
   Seiji Maekawa, Jianpeng Zhang, George Fletcher, Makoto Onizuka.
   in Proceedings of the ECML/PKDD Graph Embedding and Mining Workshop, Sep. 2019.

Journal Papers

1. GenCAT: Generating Attributed Graphs with Controlled Relationships between Classes, Attributes, and Topology. [paper] [code]
   Seiji Maekawa, Yuya Sasaki, George Fletcher, Makoto Onizuka.
   Information Systems, Feb. 2023.
2. New Attributed Graph Clustering by Bridging Attribute and Topology Spaces. [paper] [code]
   Seiji Maekawa, Koh Takeuchi, Makoto Onizuka.
   Information Processing Society of Japan, Vol.28, pp.427-435, Aug. 2020.

Domestic Conferences/Others - 国内会議・研究会等

1. 多様な人工グラフを用いた GNN によるノード分類の実証研究.
   前川 政司, 野田 昂希, 佐々木 勇和, 鬼塚 真.
   第15回データ工学と情報マネジメントに関するフォーラム（DEIM Forum 2023）, Mar. 2023.
2. コミュニティ構造を制御可能な属性付きグラフ生成. [abstract]
   前川 政司, 佐々木 勇和, George Fletcher, 鬼塚 真.
   情報処理学会第83回全国大会（IPSJ 2021）, Mar. 2021.
3. 適応的なノード埋め込みの伝搬による半教師ありノード分類モデル. [abstract]
   小川 裕也, 前川 政司, 佐々木 勇和, 藤原 靖宏, 鬼塚 真.
   情報処理学会第83回全国大会（IPSJ 2021）, Mar. 2021.
4. 時系列グラフにおける着目ノードに特化したリンク予測. [abstract]
   山口 寛人, 前川 政司, 佐々木 勇和, 鬼塚 真.
   情報処理学会第83回全国大会（IPSJ 2021）, Mar. 2021.
5. コミュニティ構造を制御する属性付きグラフ生成. [pdf]
   前川 政司, 佐々木 勇和, George Fletcher, 鬼塚 真.
   第13回データ工学と情報マネジメントに関するフォーラム（DEIM Forum 2021）, Mar. 2021.
6. 半教師ありノード分類のための適応的ノード埋め込み伝搬ニューラルネットワーク. [pdf]
   小川 裕也, 前川 政司, 佐々木 勇和, 藤原 靖宏, 鬼塚 真.
   第13回データ工学と情報マネジメントに関するフォーラム（DEIM Forum 2021）, March 2021.
7. 時系列グラフを活用する着目ノードに特化したリンク予測. [pdf]
   山口 寛人, 前川 政司, 佐々木 勇和, 鬼塚 真.
   第13回データ工学と情報マネジメントに関するフォーラム（DEIM Forum 2021）, Mar. 2021.
8. コミュニティ構造を考慮した属性付きグラフ汎用生成機構. [pdf]
   前川 政司, George Fletcher, 鬼塚 真.
   第11回データ工学と情報マネジメントに関するフォーラム（DEIM Forum 2019）, Mar. 2019.
9. 隣接性と構造類似性を考慮したグラフクラスタリング. [pdf]
   小川 裕也, 前川 政司, 竹内 孝, 佐々木 勇和, 鬼塚 真.
   第11回データ工学と情報マネジメントに関するフォーラム（DEIM Forum 2019）, Mar. 2019.
10. 属性付きグラフのための非線形関数を用いた接合加重非負値行列分解. [pdf]
    前川 政司, 竹内 孝, 佐々木 勇和, 鬼塚 真.
    第10回データ工学と情報マネジメントに関するフォーラム（DEIM Forum 2018）, Mar. 2018.

Awards

1. DEIM2019 学生プレゼンテーション賞を受賞（2019年）[Link]
2. I-Scover 利活用コンテストにて学生賞を受賞（2017年）[成果物 Link]

Activity

Talks

1. I contributed an article regarding NeurIPS2022 to The Database Community of Japan (DBSJ)　[link] (Japanese)
2. My Ph.D. thesis is featured in Information Processing Society of Japan🎉　[link] (Japanese)
3. Tutorial, "グラフ深層学習のすゝめ。" ("Introduction to Graph Neural Networks") [link] [YouTube], DEIM 2023, Mar. 2023
4. 情処ラジオ [link] [YouTube], Feb. 2023

Program Committee (Reviewing Experience)

1. IEEE BigData 2023
2. CIKM 2023, Long papers & Short papers
3. ACL 2023, Matching Workshop
4. KDD 2023, Research Track
5. NeurIPS 2022, Datasets and Benchmarks Track
6. ECML PKDD 2022, Research and Applied Data Science Tracks
7. [External Reviewer] DASFAA 2022, Research Track

Education

• Ph.D. (Information Science)
  2020-04 ~ 2023-03 @ Osaka University, Osaka, Japan. Supervised by Makoto Onizuka
  graph neural networks, synthetic graph generation
• MS (Information Science)
  2017-04 ~ 2019-03 @ Osaka University, Osaka, Japan. Supervised by Makoto Onizuka
  graph clustering, synthetic graph generation
• BE (Informatics)
  2012-04 ~ 2016-09 @ Kyoto University, Kyoto, Japan. Supervised by Marco Cuturi
  topic model, word embedding

Skills

• Python3
  • Jupyter notebook
  • pytorch, sklearn, numpy, scipy, pandas, etc.
• C++
• SQL

Page design by Ankit Sultana