papers

Publications (144)

cs.LG2023

Revisiting Over-smoothing and Over-squashing Using Ollivier-Ricci Curvature

Khang Nguyen, Hieu Nong, Vinh Nguyen +3

Graph Neural Networks (GNNs) had been demonstrated to be inherently susceptible to the problems of over-smoothing and over-squashing. These issues prohibit the ability of GNNs to m…

cs.LG2026

Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts

Minh Le, Anh Nguyen, Huy Nguyen +3

Visual Prompt Tuning (VPT) has proven effective for parameter-efficient adaptation of pre-trained vision models to downstream tasks by inserting task-specific learnable prompt toke…

cs.LG2022

On Label Shift in Domain Adaptation via Wasserstein Distance

Trung Le, Dat Do, Tuan Nguyen +4

We study the label shift problem between the source and target domains in general domain adaptation (DA) settings. We consider transformations transporting the target to source dom…

stat.ML2020

Flow-based Alignment Approaches for Probability Measures in Different Spaces

Tam Le, Nhat Ho, Makoto Yamada

Gromov-Wasserstein (GW) is a powerful tool to compare probability measures whose supports are in different metric spaces. GW suffers however from a computational drawback since it…

stat.ML2024

A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts

Huy Nguyen, Pedram Akbarian, TrungTin Nguyen +1

Mixture-of-experts (MoE) model incorporates the power of multiple submodels via gating functions to achieve greater performance in numerous regression and classification applicatio…

cs.LG2023

Designing Robust Transformers using Robust Kernel Density Estimation

Xing Han, Tongzheng Ren, Tan Minh Nguyen +3

Recent advances in Transformer architectures have empowered their empirical success in a variety of tasks across different domains. However, existing works mainly focus on predicti…