Search Results for author: Binh T. Nguyen

Found 38 papers, 18 papers with code

CompeteSMoE - Effective Training of Sparse Mixture of Experts via Competition

no code implementations4 Feb 2024 Quang Pham, Giang Do, Huy Nguyen, TrungTin Nguyen, Chenghao Liu, Mina Sartipi, Binh T. Nguyen, Savitha Ramasamy, XiaoLi Li, Steven Hoi, Nhat Ho

Sparse mixture of experts (SMoE) offers an appealing solution to scale up the model complexity beyond the mean of increasing the network's depth or width.

Semidefinite Relaxations of the Gromov-Wasserstein Distance

no code implementations22 Dec 2023 Junyu Chen, Binh T. Nguyen, Yong Sheng Soh

The Gromov-Wasserstein (GW) distance is a variant of the optimal transport problem that allows one to match objects between incomparable spaces.

A Generalization Bound of Deep Neural Networks for Dependent Data

no code implementations9 Oct 2023 Quan Huu Do, Binh T. Nguyen, Lam Si Tung Ho

Existing generalization bounds for deep neural networks require data to be independent and identically distributed (iid).

Epidemiology Generalization Bounds +1

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

1 code implementation NeurIPS 2023 Duy M. H. Nguyen, Hoang Nguyen, Nghiem T. Diep, Tan N. Pham, Tri Cao, Binh T. Nguyen, Paul Swoboda, Nhat Ho, Shadi Albarqouni, Pengtao Xie, Daniel Sonntag, Mathias Niepert

While pre-trained deep networks on ImageNet and vision-language foundation models trained on web-scale data are prevailing approaches, their effectiveness on medical tasks is limited due to the significant domain shift between natural and medical images.

Contrastive Learning Diabetic Retinopathy Grading +3

Blockwise Principal Component Analysis for monotone missing data imputation and dimensionality reduction

no code implementations10 May 2023 Tu T. Do, Mai Anh Vu, Tuan L. Vo, Hoang Thien Ly, Thu Nguyen, Steven A. Hicks, Michael A. Riegler, Pål Halvorsen, Binh T. Nguyen

To address this issue, we propose a Blockwise principal component analysis Imputation (BPI) framework for dimensionality reduction and imputation of monotone missing data.

Dimensionality Reduction Imputation

Correlation visualization under missing values: a comparison between imputation and direct parameter estimation methods

no code implementations10 May 2023 Nhat-Hao Pham, Khanh-Linh Vo, Mai Anh Vu, Thu Nguyen, Michael A. Riegler, Pål Halvorsen, Binh T. Nguyen

Correlation matrix visualization is essential for understanding the relationships between variables in a dataset, but missing data can pose a significant challenge in estimating correlation coefficients.

Imputation

Adaptive-saturated RNN: Remember more with less instability

1 code implementation ICLR 2023 Tiny Paper Track 2023 Khoi Minh Nguyen-Duy, Quang Pham, Binh T. Nguyen

Orthogonal parameterization is a compelling solution to the vanishing gradient problem (VGP) in recurrent neural networks (RNNs).

Learning for Amalgamation: A Multi-Source Transfer Learning Framework For Sentiment Classification

1 code implementation16 Mar 2023 Cuong V. Nguyen, Khiem H. Le, Anh M. Tran, Quang H. Pham, Binh T. Nguyen

Transfer learning plays an essential role in Deep Learning, which can remarkably improve the performance of the target domain, whose training data is not sufficient.

Sentiment Analysis Sentiment Classification +1

HADA: A Graph-based Amalgamation Framework in Image-text Retrieval

2 code implementations11 Jan 2023 Manh-Duy Nguyen, Binh T. Nguyen, Cathal Gurrin

It is not easy to propose a new model with a novel architecture and intensively train it on a massive dataset with many GPUs to surpass many SOTA models, which are already available to use on the Internet.

Retrieval Text Retrieval

Joint Self-Supervised Image-Volume Representation Learning with Intra-Inter Contrastive Clustering

no code implementations4 Dec 2022 Duy M. H. Nguyen, Hoang Nguyen, Mai T. N. Truong, Tri Cao, Binh T. Nguyen, Nhat Ho, Paul Swoboda, Shadi Albarqouni, Pengtao Xie, Daniel Sonntag

Recent breakthroughs in self-supervised learning (SSL) offer the ability to overcome the lack of labeled training samples by learning feature representations from unlabeled data.

Brain Segmentation Clustering +3

When can we reconstruct the ancestral state? Beyond Brownian motion

1 code implementation26 Jul 2022 Nhat L. Vu, Thanh P. Nguyen, Binh T. Nguyen, Vu Dinh, Lam Si Tung Ho

Reconstructing the ancestral state of a group of species helps answer many important questions in evolutionary biology.

A Conditional Randomization Test for Sparse Logistic Regression in High-Dimension

no code implementations29 May 2022 Binh T. Nguyen, Bertrand Thirion, Sylvain Arlot

Identifying the relevant variables for a classification model with correct confidence levels is a central but difficult task in high-dimension.

regression Test +1

Unequal Covariance Awareness for Fisher Discriminant Analysis and Its Variants in Classification

1 code implementation26 May 2022 Thu Nguyen, Quang M. Le, Son N. T. Tu, Binh T. Nguyen

Fisher Discriminant Analysis (FDA) is one of the essential tools for feature extraction and classification.

Classification

Fall detection using multimodal data

no code implementations12 May 2022 Thao V. Ha, Hoang Nguyen, Son T. Huynh, Trung T. Nguyen, Binh T. Nguyen

In recent years, the occurrence of falls has increased and has had detrimental effects on older adults.

TaDeR: A New Task Dependency Recommendation for Project Management Platform

no code implementations12 May 2022 Quynh Nguyen, Dac H. Nguyen, Son T. Huynh, Hoa K. Dam, Binh T. Nguyen

This paper proposes an efficient task dependency recommendation algorithm to suggest tasks dependent on a given task that the user has just created.

Feature Engineering Management

FPSRS: A Fusion Approach for Paper Submission Recommendation System

no code implementations12 May 2022 Son T. Huynh, Nhi Dang, Dac H. Nguyen, Phong T. Huynh, Binh T. Nguyen

Recommender systems have been increasingly popular in entertainment and consumption and are evident in academics, especially for applications that suggest submitting scientific articles to scientists.

Recommendation Systems

SimCPSR: Simple Contrastive Learning for Paper Submission Recommendation System

1 code implementation12 May 2022 Duc H. Le, Tram T. Doan, Son T. Huynh, Binh T. Nguyen

This study suggests a more advanced method for enhancing the efficiency of the paper submission recommendation system compared to previous approaches when we respectively achieve 0. 5173, 0. 8097, 0. 8862, 0. 9496 for Top 1, 3, 5, and 10 accuracies on the test set for combining the title, abstract, and keywords as input features.

Contrastive Learning Language Modelling +1

An Improved Subject-Independent Stress Detection Model Applied to Consumer-grade Wearable Devices

no code implementations18 Mar 2022 Van-Tu Ninh, Manh-Duy Nguyen, Sinéad Smyth, Minh-Triet Tran, Graham Healy, Binh T. Nguyen, Cathal Gurrin

Using our proposed model architecture, we compare the accuracy between stress detection models that use measures from each individual signal source, and one model employing the fusion of multiple sensor sources.

Management

Posterior concentration and fast convergence rates for generalized Bayesian learning

no code implementations19 Nov 2021 Lam Si Tung Ho, Binh T. Nguyen, Vu Dinh, Duy Nguyen

We prove that under the multi-scale Bernstein's condition, the generalized posterior distribution concentrates around the set of optimal hypotheses and the generalized Bayes estimator can achieve fast learning rate.

regression

An Empirical Study on GANs with Margin Cosine Loss and Relativistic Discriminator

1 code implementation21 Oct 2021 Cuong V. Nguyen, Tien-Dung Cao, Tram Truong-Huu, Khanh N. Pham, Binh T. Nguyen

In this paper, we perform an empirical study on the impact of several loss functions on the performance of standard GAN models, Deep Convolutional Generative Adversarial Networks (DCGANs).

Leaf Recognition Using Convolutional Neural Networks Based Features

1 code implementation4 Aug 2021 Boi M. Quach, Dinh V. Cuong, Nhung Pham, Dang Huynh, Binh T. Nguyen

In recent years, there is a considerable increase in the number of studies related to plant taxonomy.

An Efficient Insect Pest Classification Using Multiple Convolutional Neural Network Based Models

1 code implementation26 Jul 2021 Hieu T. Ung, Huy Q. Ung, Binh T. Nguyen

Accurate insect pest recognition is significant to protect the crop or take the early treatment on the infected yield, and it helps reduce the loss for the agriculture economy.

An Efficient Transformer-Based Model for Vietnamese Punctuation Prediction

1 code implementation IEA/AIE 2021 Hieu Tran, Cuong V. Dinh, Quang Pham, Binh T. Nguyen

In both formal and informal texts, missing punctuation marks make the texts confusing and challenging to read.

DPER: Efficient Parameter Estimation for Randomly Missing Data

1 code implementation6 Jun 2021 Thu Nguyen, Khoi Minh Nguyen-Duy, Duy Ho Minh Nguyen, Binh T. Nguyen, Bruce Alan Wade

The missing data problem has been broadly studied in the last few decades and has various applications in different areas such as statistics or bioinformatics.

Imputation

A Deep Local and Global Scene-Graph Matching for Image-Text Retrieval

1 code implementation4 Jun 2021 Manh-Duy Nguyen, Binh T. Nguyen, Cathal Gurrin

In this paper, we introduce the Local and Global Scene Graph Matching (LGSGM) model that enhances the state-of-the-art method by integrating an extra graph convolution network to capture the general information of a graph.

Graph Matching Image Retrieval +5

OASIS: An Active Framework for Set Inversion

no code implementations31 May 2021 Binh T. Nguyen, Duy M. Nguyen, Lam Si Tung Ho, Vu Dinh

In this work, we introduce a novel method for solving the set inversion problem by formulating it as a binary classification problem.

Active Learning Binary Classification

TATL: Task Agnostic Transfer Learning for Skin Attributes Detection

no code implementations4 Apr 2021 Duy M. H. Nguyen, Thu T. Nguyen, Huong Vu, Quang Pham, Manh-Duy Nguyen, Binh T. Nguyen, Daniel Sonntag

Existing skin attributes detection methods usually initialize with a pre-trained Imagenet network and then fine-tune on a medical target task.

Attribute Transfer Learning

EPEM: Efficient Parameter Estimation for Multiple Class Monotone Missing Data

1 code implementation23 Sep 2020 Thu Nguyen, Duy H. M. Nguyen, Huy Nguyen, Binh T. Nguyen, Bruce A. Wade

The problem of monotone missing data has been broadly studied during the last two decades and has many applications in different fields such as bioinformatics or statistics.

Imputation

Fast learning rates with heavy-tailed losses

no code implementations NeurIPS 2016 Vu Dinh, Lam Si Tung Ho, Duy Nguyen, Binh T. Nguyen

We study fast learning rates when the losses are not necessarily bounded and may have a distribution with heavy tails.

Clustering Quantization

Learning From Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers

no code implementations12 Aug 2014 Vu Dinh, Lam Si Tung Ho, Nguyen Viet Cuong, Duy Nguyen, Binh T. Nguyen

We prove new fast learning rates for the one-vs-all multiclass plug-in classifiers trained either from exponentially strongly mixing data or from data generated by a converging drifting distribution.

Cannot find the paper you are looking for? You can Submit a new open access paper.