LAB LOGA page on LabLog, a review site (not the lab's official page)
Machine Learning and Data Mining Lab
Machine-translated · View original
A lab for reliable machine learning that is robust to biased data.
AboutAbout the lab
Reliable machine learning, robust to biased data
The Machine Learning and Data Mining Lab aims to improve the reliability of machine learning and data mining through algorithm development and theoretical analysis based on mathematical statistics.
In particular, the lab tackles problems caused by "data bias," where the data used for learning becomes skewed unintentionally.
On the lab's website, it is introduced under the name "MDL Lab."
Key terms
- Data bias
- A state in which the data used for training is skewed in a way that departs from the intent of the people training the model.
- Transfer learning
- A method that uses a small amount of data from the prediction target to adapt a pretrained model to the target's data distribution.
- Spurious correlation
- An apparent correlation between the prediction target and an attribute that has no causal relationship to it. An example is cows and grassland backgrounds.
NewsLab news
A paper accepted at ICML 2025 wins the FY2025 Best Paper Award of the Faculty of Engineering, Information and Systems
Papers accepted at the international conferences AISTATS 2026 and ICLR 2026
A paper accepted at the international conference ICML 2025
A paper accepted at the international conference AISTATS 2025
ResearchResearch themes
Machine learning is a technology that learns from large amounts of data to make predictions, but if the training data is biased in ways that depart from what was intended, it can produce unreliable results. The lab aims to develop algorithms that behave as intended even when the data is biased.
*Illustrative imageFair Machine Learning
The lab studies algorithms that make accurate, non-discriminatory predictions even when the training data is biased with respect to attributes such as race, gender, and age. Its results include a post-processing method that efficiently controls the trade-off between fairness and predictive performance.
*Illustrative imageLearning That Adapts to Differences in Data Distribution
When the distribution of the data at training time differs from that at prediction time, the lab studies transfer learning, which adapts a model to the prediction target using a small amount of target data. It works on theoretical guarantees of success in settings where the two distributions do not overlap, and on theoretical proofs of scaling laws for pretraining.
*Illustrative imagePredictions Not Misled by Spurious Correlations
The lab studies methods that predict accurately even in situations where the correlation no longer holds, when the data to be predicted happens to correlate with an attribute that has no causal relationship to it. It is developing algorithms that reduce spurious correlations in vision-language models, even when the attributes are unknown.
MembersFaculty
The members of the Machine Learning and Data Mining Lab are faculty members, PhD, master's, and undergraduate students, and interns.As of 2026
- Assistant ProfessorKazuto Fukuchi
VoicesStudent voices
Ratings and reviews reflect the experiences of individual current or former students, not the lab's official views. Whether a lab has reviews, or how many, says nothing about the lab itself.
Students who take part in an interview may receive a thank-you gift worth ¥1,000, regardless of what they say.
Student ratings (0 students)
--
--
--
--
--
--
Student voices answer questions like these
- What's great about this lab?
- What did you learn after joining?
- What's the vibe, and what is the professor like?
- Who is this lab for?
- Where do graduates go?
Your experience can help younger students choose their lab. Your name won't be shown.
Write a lab reviewAnonymous · Your draft is saved if you stopRelatedLabs similar to Machine Learning and Data Mining Lab
Black-Box Optimization LabSchool of Informatics, College of Information ScienceOptimization of complex systems; development of general-purp…
Natural Language Processing on the Web LabSchool of Informatics, College of Information ScienceManipulating language data, from theory to Web applications …
Computational Geometry and Graphics LabSchool of Informatics, College of Information ScienceComputer graphics (CG) research: CAD, geometric modeling, us…
Cryptography and Information Security LabSchool of Informatics, College of Information ScienceProtecting important information. Broad activities from theo…The information on this page is compiled by the LabLog team from the lab's public information and interviews. For corrections or removal requests, please contact LabLog, not the lab.
Report an errorAbout the images
The top and research theme images are illustrative and were not taken at the lab. They are cropped from Wikimedia Commons images. Cropped CC BY-SA images are provided under the same CC BY-SA license as the original (version shown on each line).
- Top image: “Face Recognition Field Test at Südkreuz 17” This image is a work by Wikipedia and Wikimedia Commons user C.Suthorn. When reusing, credit me as described in the Licensing information below. I would appreciate being notified (wikimail, talk page, , Social Media) if you use my work outside Wikimedia. Do not copy this image illegally by ignoring the terms of the license below, as it is not in the public domain. If you would like special permission to use, license, or purchase the image please contact me to negotiate terms. More of my work can be found in my personal gallery or at my Peertube channel. A prepared attribution especially for use in Social Media and Print (newspapers, flyers, books, murals, mousepads, mugs, posters, t-shirts) can be copied here / CC BY-SA 4.0 (cropped)
- Fair Machine Learning: “Balance scale IMGP9755” Nikodem Nijaki / CC BY-SA 3.0 (cropped)
- Learning That Adapts to Differences in Data Distribution: “AI relation to Generative Models subset, venn diagram” The Original Benny C / CC BY-SA 4.0 (cropped)
- Predictions Not Misled by Spurious Correlations: “Camel in Gobi Desert 01” Bernard Gagnon / CC0 (cropped)
- Related lab (ブラックボックス最適化研究室): “Server Room Terminals ( )” Jon Parise / CC BY-SA 2.0 (cropped)
- Related lab (自然言語処理 on the Web 研究室): “Vecteezy stack-of-newspaper 1961329” Bernerlover / CC BY 4.0 (cropped)
- Related lab (計算幾何学と
グラフィックス研究室): “Apophysis 3D fractal ball” Garden / CC BY-SA 3.0 (cropped) - Related lab (暗号・情報セキュリティ研究室): “Padlock and key - 17c - Ryazan Kremlin Museum” Лапоть / CC0 (cropped)
About LabLog
LabLog is a lab review app for students only. Student members at each university interview students in labs and publish what they say. Student voices can only be read by students who sign up with a university email address. Operated by bestiee Inc.
Learn more about LabLog ↗Search engines and AI may reference the basic lab info and rating summaries on this page and the description of LabLog. Student voices are for student members only. Automated collection by programs (scraping, or input to or training of AI) is prohibited under Article 8 of the Terms of Service. If you need data for research or analysis, please contact us.