About
I am a Ph.D. student at the AI/ML group, TU Darmstadt, Germany.
My research interest is mainly around developing machine learning algorithms incorporating symbolic (logic, discrete structures, etc.) and numerical (probability, optimization, etc.) computations. Currently, I am mainly working on the Neuro-Symbolic approach, where the symbolic logic and neural-based models are incorporated to solve challenging problems requiring the models to perform perception from raw input and reasoning on high-level concepts.
Contact: A@B, where
(A, B) = (hikaru.shindo, tu-darmstadt.de)
Hikaru Shindo (新藤 光）
PUBLICATIONS
Journal
Hikaru Shindo, Viktor Pfanschilling, Devendra Singh Dhami, Kristian Kersting: alphaILP: Thinking Visual Scenes as Differentiable Logic Programs. Machine Learning Journal (MLJ) vol. 112, pp. 1465–1497, 2023. [paper] [code] [doc]
International Conference/Workshop
Hikaru Shindo, Manuel Brack, Gopika Sudhakaran, Devendra Singh Dhami, Patrick Schramowski, Kristian Kersting: DeiSAM: Segment Anything with Deictic Prompting. AAAI Workshop on Neuro-Symbolic Learning and Reasoning in the era of Large Language Models (NuCLeaR@AAAI) [openreview]
Quentin Delfosse*, Hikaru Shindo*, Devendra Singh Dhami, Kristian Kersting: Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction. 37th Conference on Neural Information Processing Systems (NeurIPS 2023). [paper] [code]
(* indicates equal contributions)Jingyuan Sha, Hikaru Shindo, Kristian Kersting, Devendra Singh Dhami: Neural-Symbolic Predicate Invention: Learning Relational Concepts from Visual Scenes, 17th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy 2023) [paper]
Viktor Pfanschilling, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting: Sum-Product Loop Programming: From Probabilistic Circuits to Loop Programming. 19th International Conference on Principles of Knowledge Representation and Reasoning (KR 2022). [paper].
Hikaru Shindo, Masaaki Nishino, Akihiro Yamamoto: Differentiable Inductive Logic Programming for Structured Examples. 35th AAAI Conference on Artificial Intelligence (AAAI 2021, Focus Area on Neuro-Symbolic AI), February 2021. [paper] [slides] [poster] [code] [bibtex]
Hikaru Shindo, Masaaki Nishino, Yasuaki Kobayashi, Akihiro Yamamoto: Metric Learning for Ordered Labeled Trees with pq-grams. 24th European Conference on Artificial Intelligence (ECAI 2020 ), Santiago, Spain, June 2020. [paper] [code] [bibtex]
Hikaru Shindo, Masaaki Nishino, Akihiro Yamamoto: Using Binary Decision Diagrams to Enumerate Inductive Logic Programming Solutions. 28th International Conference on Inductive Logic Programming (ILP 2018, Up-and-Coming paper), Ferrara, Italy, September 2-4, 2018. [paper] [slides] [poster] [bibtex]
Preprint
Wolfgang Stammer, Felix Friedlich, David Steinmann, Hikaru Shindo, Kristian Kersting: Learning by Self-Explaining. Preprint. 2023. [paper]
Hikaru Shindo, Viktor Pfanschilling, Devendra Singh Dhami, Kristian Kersting: Learning Differentiable Logic Programs for Abstract Visual Reasoning. Preprint. 2023. [paper] [code] [web]
Lukas Helff, Wolfgang Stammer, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting: V-LoL: A Diagnostic Dataset for Visual Logical Learning. Preprint. 2023. [paper] [code] [web]
Zihan Ye, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting: Differentiable Meta Logical Programming. Preprint. 2022. [paper]
Björn Deiseroth, Patrick Schramowski, Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting: LogicRank: Logic Induced Reranking for Generative Text-to-Image Systems. Preprint. 2022. [paper]
Hikaru Shindo, Devendra Singh Dhami, Kristian Kersting: Neuro-Symbolic Forward Reasoning. Preprint. 2021. [paper] [code]
Others
Kaneko M., Tsuji K., Masuda K., Ueno K., Henmi K., Nakagawa S., Fujita R., Suzuki K., Inoue Y., Shindo H., Konishi E., Takamatsu T., Ukimura O.: Automated urine cell image analysis with a convolutional neural network. European Urology Open Science, 19, e1357. 2020.
Service
Serving as a reviewer at: Artificial Intelligence Review (Springer), NeurIPS 2022, nCSI Workshop@NeurIPS 2022, ICML 2023, NeurIPS 2023, ICLR 2024
EDUCATION
Ph.D. student Nov 2020 -
Artificial Intelligence and Machine Learning Lab, Department of Computer Science, TU Darmstadt, Germany.
Supervised by Prof. Dr. Kristian Kersting
M.S. April 2018 - March 2020
Computational Intelligence Lab, Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Japan.
Supervised by Prof. Dr. Akihiro Yamamoto
B.S. April 2014 - March 2018
Department of Informatics and Mathematical Science, Faculty of Engineering, Kyoto University, Japan.
Supervised by Prof. Dr. Akihiro Yamamoto
EXPERIENCES
Employment
Hessen Research Associate Oct 2023-
Research Associate (Wissenschaftlicher Mitarbeiter) in SPAICER project Nov 2020 - Sep 2023
JSPS Research Fellow (日本学術振興会特別研究員DC1) April 2020 - Oct 2020
INTERNSHIPS
NTT Communication Science Laboratories, Kyoto, Japan. Research Intern (May 2019 - March 2020)
Rist Inc., Kyoto, Japan. Machine Learning Engineer (January 2018 - March 2020)
M3 Inc., Tokyo, Japan. Machine Learning Engineer (September 2018)
OTHER ACTIVITIES
Teaching Assistant. Data Science Spring School, Kyoto University, Japan. (March 2019)