no code implementations • 3 Dec 2024 • Trung-Anh Dang, Vincent Nguyen, Ngoc-Son Vu, Christel Vrain
Building on these insights, we propose Focal Neural Collapse Contrastive (FNC^2), a novel representation learning loss that effectively balances both soft and hard relationships.
no code implementations • 26 Mar 2024 • Mathieu Guilbert, Christel Vrain, Thi-Bich-Hanh Dao
In our framework an explanation of a cluster is a set of patterns, and we propose a novel interpretable constrained clustering method called ECS for declarative clustering with Explainabilty-driven Cluster Selection that integrates structural or domain expert knowledge expressed by means of constraints.
1 code implementation • 29th International Conference on Principles and Practice of Constraint Programming 2023 • Aymeric Beauchamp, Thi-Bich-Hanh Dao, Samir Loudni, Christel Vrain
Clustering is a well-known task in Data Mining that aims at grouping data instances according to their similarity.
Ranked #1 on
Incremental Constrained Clustering
on Wine
1 code implementation • 28 Sep 2021 • Antoine Guillaume, Christel Vrain, Elloumi Wael
Shapelet-based algorithms are widely used for time series classification because of their ease of interpretation, but they are currently outperformed by recent state-of-the-art approaches.
Ranked #1 on
Time Series Classification
on ArrowHead
no code implementations • 22 Nov 2020 • Antoine Guillaume, Christel Vrain, Elloumi Wael
Predictive maintenance is used in industrial applications to increase machine availability and optimize cost related to unplanned maintenance.
no code implementations • 13 Dec 2019 • Zied Bouraoui, Antoine Cornuéjols, Thierry Denœux, Sébastien Destercke, Didier Dubois, Romain Guillaume, João Marques-Silva, Jérôme Mengin, Henri Prade, Steven Schockaert, Mathieu Serrurier, Christel Vrain
Some common concerns are identified and discussed such as the types of used representation, the roles of knowledge and data, the lack or the excess of information, or the need for explanations and causal understanding.