Publications (41)
Universal Multi-Domain Translation via Diffusion Routers
Duc Kieu, Kien Do, Tuan Hoang +4
Multi-domain translation (MDT) aims to learn translations between multiple domains, yet existing approaches either require fully aligned tuples or can only handle domain pairs seen…
Theory and Evaluation Metrics for Learning Disentangled Representations
Kien Do, Truyen Tran
We make two theoretical contributions to disentanglement learning by (a) defining precise semantics of disentangled representations, and (b) establishing robust metrics for evaluat…
Outlier Detection on Mixed-Type Data: An Energy-based Approach
Kien Do, Truyen Tran, Dinh Phung +1
Outlier detection amounts to finding data points that differ significantly from the norm. Classic outlier detection methods are largely designed for single data type such as contin…
Multilevel Anomaly Detection for Mixed Data
Kien Do, Truyen Tran, Svetha Venkatesh
Anomalies are those deviating from the norm. Unsupervised anomaly detection often translates to identifying low density regions. Major problems arise when data is high-dimensional…
Semi-Supervised Learning with Variational Bayesian Inference and Maximum Uncertainty Regularization
Kien Do, Truyen Tran, Svetha Venkatesh
We propose two generic methods for improving semi-supervised learning (SSL). The first integrates weight perturbation (WP) into existing "consistency regularization" (CR) based met…
Unsupervised Anomaly Detection on Temporal Multiway Data
Duc Nguyen, Phuoc Nguyen, Kien Do +3
Temporal anomaly detection looks for irregularities over space-time. Unsupervised temporal models employed thus far typically work on sequences of feature vectors, and much less on…
Predicting the Reliability of an Image Classifier under Image Distortion
Dang Nguyen, Sunil Gupta, Kien Do +1
In image classification tasks, deep learning models are vulnerable to image distortions i.e. their accuracy significantly drops if the input images are distorted. An image-classifi…
Variational Flow Models: Flowing in Your Style
Kien Do, Duc Kieu, Toan Nguyen +4
We propose a systematic training-free method to transform the probability flow of a "linear" stochastic process characterized by the equation X_{t}=a_{t}X_{0}+Ï_{t}X_{1} into a st…
Towards Effective and Robust Neural Trojan Defenses via Input Filtering
Kien Do, Haripriya Harikumar, Hung Le +6
Trojan attacks on deep neural networks are both dangerous and surreptitious. Over the past few years, Trojan attacks have advanced from using only a single input-agnostic trigger a…
Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memory
Hung Le, Dung Nguyen, Kien Do +2
We propose Pointer-Augmented Neural Memory (PANM) to help neural networks understand and apply symbol processing to new, longer sequences of data. PANM integrates an external neura…
Memory-Augmented Theory of Mind Network
Dung Nguyen, Phuoc Nguyen, Hung Le +3
Social reasoning necessitates the capacity of theory of mind (ToM), the ability to contextualise and attribute mental states to others without having access to their internal cogni…
Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation
Kien Do, Hung Le, Dung Nguyen +5
Data-free Knowledge Distillation (DFKD) has attracted attention recently thanks to its appealing capability of transferring knowledge from a teacher network to a student network wi…
Causal Inference via Style Transfer for Out-of-distribution Generalisation
Toan Nguyen, Kien Do, Duc Thanh Nguyen +2
Out-of-distribution (OOD) generalisation aims to build a model that can generalise well on an unseen target domain using knowledge from multiple source domains. To this end, the mo…
h-Edit: Effective and Flexible Diffusion-Based Editing via Doob's h-Transform
Toan Nguyen, Kien Do, Duc Kieu +1
We introduce a theoretical framework for diffusion-based image editing by formulating it as a reverse-time bridge modeling problem. This approach modifies the backward process of a…
Black-box Few-shot Knowledge Distillation
Dang Nguyen, Sunil Gupta, Kien Do +1
Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of…
Knowledge Graph Embedding with Multiple Relation Projections
Kien Do, Truyen Tran, Svetha Venkatesh
Knowledge graphs contain rich relational structures of the world, and thus complement data-driven machine learning in heterogeneous data. One of the most effective methods in repre…
Generating Realistic Tabular Data with Large Language Models
Dang Nguyen, Sunil Gupta, Kien Do +2
While most generative models show achievements in image data generation, few are developed for tabular data generation. Recently, due to success of large language models (LLM) in d…
Beyond Surprise: Improving Exploration Through Surprise Novelty
Hung Le, Kien Do, Dung Nguyen +1
We present a new computing model for intrinsic rewards in reinforcement learning that addresses the limitations of existing surprise-driven explorations. The reward is the novelty…
Multi-Reference Preference Optimization for Large Language Models
Hung Le, Quan Tran, Dung Nguyen +4
How can Large Language Models (LLMs) be aligned with human intentions and values? A typical solution is to gather human preference on model outputs and finetune the LLMs accordingl…
Clustering by Maximizing Mutual Information Across Views
Kien Do, Truyen Tran, Svetha Venkatesh
We propose a novel framework for image clustering that incorporates joint representation learning and clustering. Our method consists of two heads that share the same backbone netw…
Learning to Constrain Policy Optimization with Virtual Trust Region
Hung Le, Thommen Karimpanal George, Majid Abdolshah +4
We introduce a constrained optimization method for policy gradient reinforcement learning, which uses a virtual trust region to regulate each policy update. In addition to using th…
Semantic Host-free Trojan Attack
Haripriya Harikumar, Kien Do, Santu Rana +2
In this paper, we propose a novel host-free Trojan attack with triggers that are fixed in the semantic space but not necessarily in the pixel space. In contrast to existing Trojan…
Graph Transformation Policy Network for Chemical Reaction Prediction
Kien Do, Truyen Tran, Svetha Venkatesh
We address a fundamental problem in chemistry known as chemical reaction product prediction. Our main insight is that the input reactant and reagent molecules can be jointly repres…
Attentional Multilabel Learning over Graphs: A Message Passing Approach
Kien Do, Truyen Tran, Thin Nguyen +1
We address a largely open problem of multilabel classification over graphs. Unlike traditional vector input, a graph has rich variable-size substructures which are related to the l…
Episodic Policy Gradient Training
Hung Le, Majid Abdolshah, Thommen K. George +3
We introduce a novel training procedure for policy gradient methods wherein episodic memory is used to optimize the hyperparameters of reinforcement learning algorithms on-the-fly.…
Improving Diversity in Black-box Few-shot Knowledge Distillation
Tri-Nhan Vo, Dang Nguyen, Kien Do +1
Knowledge distillation (KD) is a well-known technique to effectively compress a large network (teacher) to a smaller network (student) with little sacrifice in performance. However…
Bidirectional Diffusion Bridge Models
Duc Kieu, Kien Do, Toan Nguyen +2
Diffusion bridges have shown potential in paired image-to-image (I2I) translation tasks. However, existing methods are limited by their unidirectional nature, requiring separate mo…
Finding the Trigger: Causal Abductive Reasoning on Video Events
Thao Minh Le, Vuong Le, Kien Do +3
This paper introduces a new problem, Causal Abductive Reasoning on Video Events (CARVE), which involves identifying causal relationships between events in a video and generating hy…
FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
Minh Khoa Le, Kien Do, Duc Thanh Nguyen +1
High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion metho…
Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning
Hung Le, Kien Do, Dung Nguyen +2
Effective decision-making in partially observable environments demands robust memory management. Despite their success in supervised learning, current deep-learning memory models s…
Learning Deep Matrix Representations
Kien Do, Truyen Tran, Svetha Venkatesh
We present a new distributed representation in deep neural nets wherein the information is represented in native form as a matrix. This differs from current neural architectures th…
Reviving Error Correction in Modern Deep Time-Series Forecasting
Minh Hoang Nguyen, Dai Do, Huu Hiep Nguyen +3
Modern deep-learning models have achieved remarkable success in time-series forecasting. Yet, their performance degrades in long-term prediction due to error accumulation in autore…
Diverse Image Priors for Black-box Data-free Knowledge Distillation
Tri-Nhan Vo, Dang Nguyen, Trung Le +2
Knowledge distillation (KD) represents a vital mechanism to transfer expertise from complex teacher networks to efficient student models. However, in decentralized or secure AI eco…
Learning Theory of Mind via Dynamic Traits Attribution
Dung Nguyen, Phuoc Nguyen, Hung Le +3
Machine learning of Theory of Mind (ToM) is essential to build social agents that co-live with humans and other agents. This capacity, once acquired, will help machines infer the m…
Learning Structural Causal Models from Ordering: Identifiable Flow Models
Minh Khoa Le, Kien Do, Truyen Tran
In this study, we address causal inference when only observational data and a valid causal ordering from the causal graph are available. We introduce a set of flow models that can…
Revisiting the Dataset Bias Problem from a Statistical Perspective
Kien Do, Dung Nguyen, Hung Le +6
In this paper, we study the "dataset bias" problem from a statistical standpoint, and identify the main cause of the problem as the strong correlation between a class attribute u a…
Domain Generalisation via Risk Distribution Matching
Toan Nguyen, Kien Do, Bao Duong +1
We propose a novel approach for domain generalisation (DG) leveraging risk distributions to characterise domains, thereby achieving domain invariance. In our findings, risk distrib…
Defense Against Multi-target Trojan Attacks
Haripriya Harikumar, Santu Rana, Kien Do +4
Adversarial attacks on deep learning-based models pose a significant threat to the current AI infrastructure. Among them, Trojan attacks are the hardest to defend against. In this…
DeepProcess: Supporting business process execution using a MANN-based recommender system
Asjad Khan, Hung Le, Kien Do +4
Process-aware Recommender systems can provide critical decision support functionality to aid business process execution by recommending what actions to take next. Based on recent a…
Face Swapping as A Simple Arithmetic Operation
Truong Vu, Kien Do, Khang Nguyen +1
We propose a novel high-fidelity face swapping method called "Arithmetic Face Swapping" (AFS) that explicitly disentangles the intermediate latent space W+ of a pretrained StyleGAN…
Large Language Models for Imbalanced Classification: Diversity makes the difference
Dang Nguyen, Sunil Gupta, Kien Do +4
Oversampling is one of the most widely used approaches for addressing imbalanced classification. The core idea is to generate additional minority samples to rebalance the dataset.…