Tabular-data Rehearsal-based Incremental Lifelong Learning Framework (TRIL3)
Continual Learning paradigm avoiding Catastrophic Forgetting for generic tabular-data problems.
Asset Description
New methodology, coined as Tabular-data Rehearsal-based Incremental Lifelong Learning framework (TRIL3), designed to address the phenomenon of catastrophic forgetting in tabular data classification problems.
Asset Details
Dataset Information
Continual learning (CL) poses the important challenge of adapting to evolving data distributions without forgetting previously acquired knowledge while consolidating new knowledge. In this paper, we introduce a new methodology, coined as Tabular-data Rehearsal-based Incremental Lifelong Learning framework (TRIL3), designed to address the phenomenon of catastrophic forgetting in tabular data classification problems. TRIL3 uses the prototype-based incremental generative model XuILVQ to generate synthetic data to preserve old knowledge and the DNDF algorithm, which was modified to run in an incremental way, to learn classification tasks for tabular data, without storing old samples. After different tests to obtain the adequate percentage of synthetic data and to compare TRIL3 with other CL available proposals, we can conclude that the performance of TRIL3 outstands other options in the literature using only 50% of synthetic data.
Usage
The publication is available in the link. Please use the following reference: García-Santaclara, Pablo & Fernández-Castro, Bruno & Redondo, Rebeca. (2024). Overcoming Catastrophic Forgetting in Tabular Data Classification: A Pseudorehearsal-based approach. 10.48550/arXiv.2407.09039
Maturity
Not available
Licence
Not available
Resources
- The publication is available here
- For further information, please contact mmarquez@gradiant.org.
- Provided by GRADIANT
Acknowledgement
Part of the associated work to this paper was carried out by Gradiant under the AI REDGIO 5.0 project initiative.