2 citations · 4 across the 4 of their papers we have counts for
3 papers · 1 filter
Confine to the Task, Anchor the Rest: Concept-Guided Retention Regularizer for Parameter-Efficient Fine-Tuning
Ibna Kowsar, Ivan Medri, Fanyu Meng +1
Parameter-efficient fine-tuning (PEFT) has been widely used, yet the adapted model suffers catastrophic forgetting of pre-trained knowledge. While most existing work hardens the ad…
Attention versus Contrastive Learning of Tabular Data -- A Data-centric Benchmarking
Shourav B. Rabbani, Ivan V. Medri, Manar D. Samad
Despite groundbreaking success in image and text learning, deep learning has not achieved significant improvements against traditional machine learning (ML) when it comes to tabula…
Deep Clustering of Tabular Data by Weighted Gaussian Distribution Learning
Shourav B. Rabbani, Ivan V. Medri, Manar D. Samad
Deep learning methods are primarily proposed for supervised learning of images or text with limited applications to clustering problems. In contrast, tabular data with heterogeneou…