6 papers
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…
Generalized Context in Cross Attention for Transfer Learning of Disjoint Tabular Data
Kazi F. Akhter, Ibna Kowsar, Manar D. Samad
Unlike images and text, applying transfer learning to tabular data is challenging due to heterogeneity in feature types, structures, and semantics across disparate domains. Existin…
LATTLE: LLM Attention Transplant for Transfer Learning of Tabular Data Across Disparate Domains
Ibna Kowsar, Kazi F. Akhter, Manar D. Samad
Transfer learning on tabular data is challenging due to disparate feature spaces across domains, in contrast to the homogeneous structures of image and text. Large language models…
Imputation-free Learning of Tabular Data with Missing Values using Incremental Feature Partitions in Transformer
Manar D. Samad, Kazi Fuad B. Akhter, Shourav B. Rabbani +1
Tabular data sets with varying missing values are prepared for machine learning using an arbitrary imputation strategy. Synthetic values generated by imputation models often raise…
Transfer Learning of Tabular Data by Finetuning Large Language Models
Shourav B. Rabbani, Ibna Kowsar, Manar D. Samad
Despite the artificial intelligence (AI) revolution, deep learning has yet to achieve much success with tabular data due to heterogeneous feature space and limited sample sizes wit…
DeepIFSAC: Deep Imputation of Missing Values Using Feature and Sample Attention within Contrastive Framework
Ibna Kowsar, Shourav B. Rabbani, Yina Hou +1
Missing values of varying patterns and rates in real-world tabular data pose a significant challenge in developing reliable data-driven models. The most commonly used statistical a…