AIConfPaper
← Search

Trong Nghia Hoang

21 accepted papers

2026

ForeSWE: Forecasting Snow-Water Equivalent with an Uncertainty-Aware Attention Model

Krishu K Thapa, Supriya Savalkar, Bhupinderjeet Singh, Trong Nghia Hoang, Kirti Rajagopalan, Ananth Kalyanaraman
AAAI 2026technical

Various complex water management decisions are made in snow-dominant watersheds with the knowledge of Snow-Water Equivalent (SWE)---a key measure widely used to estimate the water content of a snowpack. However, forecasting SWE is challenging because SWE is influenced by various factors including to

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Federated Prompt-Tuning with Heterogeneous and Incomplete Multimodal Client Data

Thu Hang Phung, Duong M. Nguyen, Thanh Trung Huynh, Quoc Viet Hung Nguyen, Trong Nghia Hoang, Phi Le Nguyen
ICCV 2025poster

This paper introduces a generalized federated prompt-tuning framework for practical scenarios where local datasets are multi-modal and exhibit different distributional patterns of missing features at the input level. The proposed framework bridges the gap between federated learning and multi-modal p…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data

Manh Duong Nguyen, Trong Nghia Hoang, Thanh Trung Huynh, Quoc Viet Hung Nguyen, Phi Le Nguyen
NeurIPS 2025poster

Multimodal federated learning in real-world settings often encounters incomplete and heterogeneous data across clients. This results in misaligned local feature representations that limit the effectiveness of model aggregation. Unlike prior work that assumes either differing modality sets without mi…

Cited by 0Source ↗code ↗Scholar ↗
2025

ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge

Manh Cuong Dao, The Hung Tran, Phi Le Nguyen, Thao Nguyen Truong, Trong Nghia Hoang
NeurIPS 2025spotlight

This paper studies the black-box optimization task which aims to find the maxima of a black-box function using a static set of its observed input-output pairs. This is often achieved via learning and optimizing a surrogate function with that offline data. Alternatively, it can also be framed as an i…

Cited by 0Source ↗code ↗Scholar ↗
2024

Boosting Offline Optimizers with Surrogate Sensitivity

Manh Cuong Dao, Phi Le Nguyen, Thao Nguyen Truong, Trong Nghia Hoang
ICML 2024poster

Offline optimization is an important task in numerous material engineering domains where online experimentation to collect data is too expensive and needs to be replaced by an in silico maximization of a surrogate of the black-box function. Although such a surrogate can be learned from offline data,…

Cited by 6Source ↗PDF ↗Scholar ↗
2024

Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques

Manh Cuong Dao, Phi Le Nguyen, Thao Nguyen Truong, Trong Nghia Hoang
NeurIPS 2024poster

Offline optimization has recently emerged as an increasingly popular approach to mitigate the prohibitively expensive cost of online experimentation. The key idea is to learn a surrogate of the black-box function that underlines the target experiment using a static (offline) dataset of its previous…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Learning Surrogates for Offline Black-Box Optimization via Gradient Matching

Minh Hoang, Azza Fadhel, Aryan Deshwal, Jana Doppa, Trong Nghia Hoang
ICML 2024poster

Offline design optimization problem arises in numerous science and engineering applications including material and chemical design, where expensive online experimentation necessitates the use of *in silico* surrogate functions to predict and maximize the target objective over candidate designs. Alth…

Cited by 6Source ↗PDF ↗Scholar ↗
2024

Offline Model-Based Optimization via Policy-Guided Gradient Search

Yassine Chemingui, Aryan Deshwal, Trong Nghia Hoang, Janardhan Rao Doppa
AAAI 2024technical

Offline optimization is an emerging problem in many experimental engineering domains including protein, drug or aircraft design, where online experimentation to collect evaluation data is too expensive or dangerous. To avoid that, one has to optimize an unknown function given only its offline evalua…

Cited by 11Source ↗PDF ↗code ↗Scholar ↗
2024

Probabilistic Federated Prompt-Tuning with Non-IID and Imbalanced Data

Pei-Yau Weng, Minh Hoang, Lam M. Nguyen, My T. Thai, Tsui-Wei Weng, Trong Nghia Hoang
NeurIPS 2024poster

Fine-tuning pre-trained models is a popular approach in machine learning for solving complex tasks with moderate data. However, fine-tuning the entire pre-trained model is ineffective in federated data scenarios where local data distributions are diversely skewed. To address this, we explore integra…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Revisiting Kernel Attention with Correlated Gaussian Process Representation

Long Minh Bui, Tho Tran Huu, Duy Dinh, Tan Minh Nguyen, Trong Nghia Hoang
UAI 2024poster

Transformers have increasingly become the de facto method to model sequential data with state-of-the-art performance. Due to its widespread use, being able to estimate and calibrate its modeling uncertainty is important to understand and design robust transformer models. To achieve this, previous wo…

Cited by 3Source ↗PDF ↗Scholar ↗
2023

Federated learning of models pre-trained on different features with consensus graphs

Tengfei Ma, Trong Nghia Hoang, Jie Chen
UAI 2023poster

Learning an effective global model on private and decentralized datasets has become an increasingly important challenge of machine learning when applied in practice. Existing distributed learning paradigms, such as Federated Learning, enable this via model aggregation which enforces a strong form of…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2023

Incentives in Private Collaborative Machine Learning

Rachael Hwee Ling Sim, Yehong Zhang, Trong Nghia Hoang, Xinyi Xu, Bryan Kian Hsiang Low, Patrick Jaillet
NeurIPS 2023poster

Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation. Existing data valuation methods fairly value and reward each party based on shared data or model parameters but neglect the privacy risks involved. To address this, we int…

Cited by 7Source ↗PDF ↗Scholar ↗
2023

Personalized federated domain adaptation for item-to-item recommendation

Ziwei Fan, Hao Ding, Anoop Deoras, Trong Nghia Hoang
UAI 2023poster

Item-to-Item (I2I) recommendation is an important function that suggests replacement or complement options for an item based on their functional similarities or synergies. To capture such item relationships effectively, the recommenders need to understand why subsets of items are co-viewed or co-pur…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2023

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

Linbo Liu, Youngsuk Park, Trong Nghia Hoang, Hilaf Hasson, Luke Huan
ICLR 2023poster

This work studies the threats of adversarial attack on multivariate probabilistic forecasting models and viable defense mechanisms. Our studies discover a new attack pattern that negatively impact the forecasting of a target time series via making strategic, sparse (imperceptible) modifications to t…

Cited by 18Source ↗PDF ↗code ↗Scholar ↗
2022

Bayesian federated estimation of causal effects from observational data

Thanh Vinh Vo, Young Lee, Trong Nghia Hoang, Tze-Yun Leong
UAI 2022poster

We propose a Bayesian framework for estimating causal effects from federated observational data sources. Bayesian causal inference is an important approach to learning the distribution of the causal estimands and understanding the uncertainty of causal effects. Our framework estimates the posterior…

Cited by 23Source ↗PDF ↗code ↗Scholar ↗
2018

Near-Optimal Adversarial Policy Switching for Decentralized Asynchronous Multi-Agent Systems

Trong Nghia Hoang, Yuchen Xiao, Kavinayan Sivakumar, Christopher Amato, Jonathan P. Howl
ICRA 2018poster

A key challenge in multi-robot and multi-agent systems is generating solutions that are robust to other self-interested or even adversarial parties who actively try to prevent the agents from achieving their goals. The practicality of existing works addressing this challenge is limited to only small…

Cited by 16Source ↗Scholar ↗
2016

A Distributed Variational Inference Framework for Unifying Parallel Sparse Gaussian Process Regression Models

Trong Nghia Hoang, Quang Minh Hoang, Bryan Kian Hsiang Low
ICML 2016poster

This paper presents a novel distributed variational inference framework that unifies many parallel sparse Gaussian process regression (SGPR) models for scalable hyperparameter learning with big data. To achieve this, our framework exploits a structure of correlated noise process model that represent…

Cited by 62Source ↗PDF ↗Scholar ↗
2015

A Unifying Framework of Anytime Sparse Gaussian Process Regression Models with Stochastic Variational Inference for Big Data

Trong Nghia Hoang, Quang Minh Hoang, Bryan Kian Hsiang Low
ICML 2015poster

This paper presents a novel unifying framework of anytime sparse Gaussian process regression (SGPR) models that can produce good predictive performance fast and improve their predictive performance over time. Our proposed unifying framework reverses the variational inference procedure to theoretical…

Cited by 109Source ↗PDF ↗Scholar ↗