61 citations
- The University of TokyoJP4 papers
- Fujitsu (China)CN3 papers
- National Institute of Advanced Industrial Science and TechnologyJP3 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Fujitsu (United Kingdom)GB2 papers
- University of ManchesterGB2 papers
- University of TsukubaJP2 papers
- Aalborg UniversityDK1 paper
- Baidu (China)CN1 paper
- Bank of JapanJP1 paper
- Beijing University of Posts and TelecommunicationsCN1 paper
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR1 paper
10 papers · 1 filter
Generating gradients in the energy landscape using rectified linear type cost functions for efficiently solving 0/1 matrix factorization in Simulated Annealing
Makiko Konoshima, Hirotaka Tamura, Yoshiyuki Kabashima
The 0/1 matrix factorization defines matrix products using logical AND and OR as product-sum operators, revealing the factors influencing various decision processes. Instances and…
Fair Oversampling Technique using Heterogeneous Clusters
Ryosuke Sonoda
Class imbalance and group (e.g., race, gender, and age) imbalance are acknowledged as two reasons in data that hinder the trade-off between fairness and utility of machine learning…
Exploring the Whole Rashomon Set of Sparse Decision Trees
Rui Xin, Chudi Zhong, Zhi Chen +3
In any given machine learning problem, there may be many models that could explain the data almost equally well. However, most learning algorithms return only one of these models,…
Practical Insights of Repairing Model Problems on Image Classification
Akihito Yoshii, Susumu Tokumoto, Fuyuki Ishikawa
Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is…
SapientML: Synthesizing Machine Learning Pipelines by Learning from Human-Written Solutions
Ripon K. Saha, Akira Ura, Sonal Mahajan +6
Automatic machine learning, or AutoML, holds the promise of truly democratizing the use of machine learning (ML), by substantially automating the work of data scientists. However,…
Inter-domain Multi-relational Link Prediction
Luu Huu Phuc, Koh Takeuchi, Seiji Okajima +4
Multi-relational graph is a ubiquitous and important data structure, allowing flexible representation of multiple types of interactions and relations between entities. Similar to o…