arXiv subjects

Duong Nguyen

Publications and source records attributed to Duong Nguyen.

At least 19 recordsLinked to original sources

arXiv2026

TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models

Tabular foundation models (TFMs), such as TabPFN-2.6, TabICLv2, ConTextTab, Mitra, LimiX, and TabDPT, achieve strong zero-shot performance through in-context learning, but their inductive biases remain fixed at inference time. Adapting a pretrained TFM to a specific dataset or task typically requires either full fine-tuning, which is computationally expensive, or parameter-efficient tuning methods (PEFT) such as LoRA, which must be tailored to the internal architecture of each TFM. Furthermore, the evidence on whether weight-space fine-tuning improves accuracy or calibration is mixed \citep{tanna_exploring_2026,rubachev_finetuning_2025}. We introduce TFM-Retouche, a lightweight input-space residual adapter that is architecture-agnostic by design with respect to the frozen TFM backbone. TFM-Retouche learns a small residual correction in the input space to align the input data with the inductive biases of the pretrained model. The adapter is trained end-to-end through the frozen TFM, with a post-training identity guard that falls back to the unmodified TFM whenever adaptation does not help on held-out validation. On TabArena-Lite (51 datasets spanning binary classification, multiclass classification, and regression), TabICLv2-Retouche -- the framework instantiated on TabICLv2 -- is the top-ranked method on the leaderboard with light per-task tuning and ensembling, lifting aggregate Elo by +56 over the frozen TabICLv2 base and sitting on the Pareto front of predictive quality versus both training and inference time.

cs.LG↗

arXiv2026

StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models

Recent token merging techniques for Vision Transformers (ViTs) provide substantial speedups by reducing the number of tokens processed by self-attention, often without retraining. However, their direct application to the Segment Anything Model (SAM) family is nontrivial: SAM's image encoder mixes windowed and global attention, and its mask decoder relies on dense, prompt-conditioned features for precise boundary prediction. We systematically evaluate representative token-merging methods on SAM and Medical SAM in a strict off-the-shelf setting, and find that existing destination-selection heuristics can erode boundaries and leak prompt information as merge rates increase. We propose \textbf{StructSAM}, a resolution-preserving merge-unmerge framework tailored to SAM. StructSAM computes a lightweight token-energy score from first-order feature gradients, uses grid-based flatness screening to protect boundary and prompt regions, and merges tokens within flat areas toward low-energy destinations with explicit token recovery. We further provide a spectral graph coarsening view showing that score-guided merging yields bounded Laplacian spectral distortion compared to random or window-restricted baselines. Across eight natural and medical benchmarks, StructSAM reduces encoder FLOPs by 25-30\% (up to 40\%+ with prompt-aware merging) with minor drops in mIoU/Dice, consistently outperforming ToMe, PiToMe, ToMeSD, VidToMe, and ALGM at the same compute.

cs.CV↗

arXiv2025

VulGuard: An Unified Tool for Evaluating Just-In-Time Vulnerability Prediction Models

We present VulGuard, an automated tool designed to streamline the extraction, processing, and analysis of commits from GitHub repositories for Just-In-Time vulnerability prediction (JIT-VP) research. VulGuard automatically mines commit histories, extracts fine-grained code changes, commit messages, and software engineering metrics, and formats them for downstream analysis. In addition, it integrates several state-of-the-art vulnerability prediction models, allowing researchers to train, evaluate, and compare models with minimal setup. By supporting both repository-scale mining and model-level experimentation within a unified framework, VulGuard addresses key challenges in reproducibility and scalability in software security research. VulGuard can also be easily integrated into the CI/CD pipeline. We demonstrate the effectiveness of the tool in two influential open-source projects, FFmpeg and the Linux kernel, highlighting its potential to accelerate real-world JIT-VP research and promote standardized benchmarking. A demo video is available at: https://youtu.be/j96096-pxbs

cs.SE↗

arXiv2025

Domain Generalization via Pareto Optimal Gradient Matching

In this study, we address the gradient-based domain generalization problem, where predictors aim for consistent gradient directions across different domains. Existing methods have two main challenges. First, minimization of gradient empirical distance or gradient inner products (GIP) leads to gradient fluctuations among domains, thereby hindering straightforward learning. Second, the direct application of gradient learning to the joint loss function can incur high computation overheads due to second-order derivative approximation. To tackle these challenges, we propose a new Pareto Optimality Gradient Matching (POGM) method. In contrast to existing methods that add gradient matching as regularization, we leverage gradient trajectories as collected data and apply independent training at the meta-learner. In the meta-update, we maximize GIP while limiting the learned gradient from deviating too far from the empirical risk minimization gradient trajectory. By doing so, the aggregate gradient can incorporate knowledge from all domains without suffering gradient fluctuation towards any particular domain. Experimental evaluations on datasets from DomainBed demonstrate competitive results yielded by POGM against other baselines while achieving computational efficiency.

cs.LG↗

arXiv2025

Toward Realistic Evaluations of Just-In-Time Vulnerability Prediction

Modern software systems are increasingly complex, presenting significant challenges in quality assurance. Just-in-time vulnerability prediction (JIT-VP) is a proactive approach to identifying vulnerable commits and providing early warnings about potential security risks. However, we observe that current JIT-VP evaluations rely on an idealized setting, where the evaluation datasets are artificially balanced, consisting exclusively of vulnerability-introducing and vulnerability-fixing commits. To address this limitation, this study assesses the effectiveness of JIT-VP techniques under a more realistic setting that includes both vulnerability-related and vulnerability-neutral commits. To enable a reliable evaluation, we introduce a large-scale public dataset comprising over one million commits from FFmpeg and the Linux kernel. Our empirical analysis of eight state-of-the-art JIT-VP techniques reveals a significant decline in predictive performance when applied to real-world conditions; for example, the average PR-AUC on Linux drops 98% from 0.805 to 0.016. This discrepancy is mainly attributed to the severe class imbalance in real-world datasets, where vulnerability-introducing commits constitute only a small fraction of all commits. To mitigate this issue, we explore the effectiveness of widely adopted techniques for handling dataset imbalance, including customized loss functions, oversampling, and undersampling. Surprisingly, our experimental results indicate that these techniques are ineffective in addressing the imbalance problem in JIT-VP. These findings underscore the importance of realistic evaluations of JIT-VP and the need for domain-specific techniques to address data imbalance in such scenarios.

cs.SE↗

arXiv2025

Foundation models for time series forecasting: Application in conformal prediction

The zero-shot capabilities of foundation models (FMs) for time series forecasting offer promising potentials in conformal prediction, as most of the available data can be allocated to calibration. This study compares the performance of Time Series Foundation Models (TSFMs) with traditional methods, including statistical models and gradient boosting, within a conformal prediction setting. Our findings highlight two key advantages of TSFMs. First, when the volume of data is limited, TSFMs provide more reliable conformalized prediction intervals than classic models, thanks to their superior predictive accuracy. Second, the calibration process is more stable because more data are used for calibration. Morever, the fewer data available, the more pronounced these benefits become, as classic models require a substantial amount of data for effective training. These results underscore the potential of foundation models in improving conformal prediction reliability in time series applications, particularly in data-constrained cases. All the code to reproduce the experiments is available.

cs.LG↗

arXiv2024

United We Stand: Decentralized Multi-Agent Planning With Attrition

Decentralized planning is a key element of cooperative multi-agent systems for information gathering tasks. However, despite the high frequency of agent failures in realistic large deployment scenarios, current approaches perform poorly in the presence of failures, by not converging at all, and/or by making very inefficient use of resources (e.g. energy). In this work, we propose Attritable MCTS (A-MCTS), a decentralized MCTS algorithm capable of timely and efficient adaptation to changes in the set of active agents. It is based on the use of a global reward function for the estimation of each agent's local contribution, and regret matching for coordination. We evaluate its effectiveness in realistic data-harvesting problems under different scenarios. We show both theoretically and experimentally that A-MCTS enables efficient adaptation even under high failure rates. Results suggest that, in the presence of frequent failures, our solution improves substantially over the best existing approaches in terms of global utility and scalability.

cs.MA↗

arXiv2024

Revisiting LARS for Large Batch Training Generalization of Neural Networks

This paper explores Large Batch Training techniques using layer-wise adaptive scaling ratio (LARS) across diverse settings, uncovering insights. LARS algorithms with warm-up tend to be trapped in sharp minimizers early on due to redundant ratio scaling. Additionally, a fixed steep decline in the latter phase restricts deep neural networks from effectively navigating early-phase sharp minimizers. Building on these findings, we propose Time Varying LARS (TVLARS), a novel algorithm that replaces warm-up with a configurable sigmoid-like function for robust training in the initial phase. TVLARS promotes gradient exploration early on, surpassing sharp optimizers and gradually transitioning to LARS for robustness in later phases. Extensive experiments demonstrate that TVLARS consistently outperforms LARS and LAMB in most cases, with up to 2\% improvement in classification scenarios. Notably, in all self-supervised learning cases, TVLARS dominates LARS and LAMB with performance improvements of up to 10\%.

cs.LG↗

arXiv2024

Satisfaction and Regret in Stackelberg Games

This paper introduces the new concept of (follower) satisfaction in Stackelberg games and compares the standard Stackelberg game with its satisfaction version. Simulation results are presented which suggest that the follower adopting satisfaction generally increases leader utility. This important new result is proven for the case where leader strategies to commit to are restricted to be deterministic (pure strategies). The paper then addresses the application of regret based algorithms to the Stackelberg problem. Although it is known that the follower adopts a no-regret position in a Stackelberg solution, this is not generally the case for the leader. The report examines the convergence behaviour of unconditional and conditional regret matching (RM) algorithms in the Stackelberg setting. The paper shows that, in the examples considered, that these algorithms either converge to any pure Nash equilibria for the simultaneous move game, or to some mixed strategies which do not have the "no-regret" property. In one case, convergence of the conditional RM algorithm over both players to a solution "close" to the Stackelberg case was observed. The paper argues that further research in this area, in particular when applied in the satisfaction setting could be fruitful.

cs.GT↗

arXiv2024

Magazine Supply Optimization: a Case-study

Supply optimization is a complex and challenging task in the magazine retail industry because of the fixed inventory assumption, irregular sales patterns, and varying product and point-of-sale characteristics. We introduce AthenIA, an industrialized magazine supply optimization solution that plans the supply for over 20,000 points of sale in France. We modularize the supply planning process into a four-step pipeline: demand sensing, optimization, business rules, and operating. The core of the solution is a novel group conformalized quantile regression method that integrates domain expert insights, coupled with a supply optimization technique that balances the costs of out-of-stock against the costs of over-supply. AthenIA has proven to be a valuable tool for magazine publishers, particularly in the context of evolving economic and ecological challenges.

cs.AI↗

arXiv2024

How Homogenizing the Channel-wise Magnitude Can Enhance EEG Classification Model?

A significant challenge in the electroencephalogram EEG lies in the fact that current data representations involve multiple electrode signals, resulting in data redundancy and dominant lead information. However extensive research conducted on EEG classification focuses on designing model architectures without tackling the underlying issues. Otherwise, there has been a notable gap in addressing data preprocessing for EEG, leading to considerable computational overhead in Deep Learning (DL) processes. In light of these issues, we propose a simple yet effective approach for EEG data pre-processing. Our method first transforms the EEG data into an encoded image by an Inverted Channel-wise Magnitude Homogenization (ICWMH) to mitigate inter-channel biases. Next, we apply the edge detection technique on the EEG-encoded image combined with skip connection to emphasize the most significant transitions in the data while preserving structural and invariant information. By doing so, we can improve the EEG learning process efficiently without using a huge DL network. Our experimental evaluations reveal that we can significantly improve (i.e., from 2% to 5%) over current baselines.

eess.SP↗

arXiv2024

Revisiting the Disequilibrium Issues in Tackling Heart Disease Classification Tasks

In the field of heart disease classification, two primary obstacles arise. Firstly, existing Electrocardiogram (ECG) datasets consistently demonstrate imbalances and biases across various modalities. Secondly, these time-series data consist of diverse lead signals, causing Convolutional Neural Networks (CNNs) to become overfitting to the one with higher power, hence diminishing the performance of the Deep Learning (DL) process. In addition, when facing an imbalanced dataset, performance from such high-dimensional data may be susceptible to overfitting. Current efforts predominantly focus on enhancing DL models by designing novel architectures, despite these evident challenges, seemingly overlooking the core issues, therefore hindering advancements in heart disease classification. To address these obstacles, our proposed approach introduces two straightforward and direct methods to enhance the classification tasks. To address the high dimensionality issue, we employ a Channel-wise Magnitude Equalizer (CME) on signal-encoded images. This approach reduces redundancy in the feature data range, highlighting changes in the dataset. Simultaneously, to counteract data imbalance, we propose the Inverted Weight Logarithmic Loss (IWL) to alleviate imbalances among the data. When applying IWL loss, the accuracy of state-of-the-art models (SOTA) increases up to 5% in the CPSC2018 dataset. CME in combination with IWL also surpasses the classification results of other baseline models from 5% to 10%.

cs.LG↗

arXiv2024

PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation

Beyond class frequency, we recognize the impact of class-wise relationships among various class-specific predictions and the imbalance in label masks on long-tailed segmentation learning. To address these challenges, we propose an innovative Pixel-wise Adaptive Training (PAT) technique tailored for long-tailed segmentation. PAT has two key features: 1) class-wise gradient magnitude homogenization, and 2) pixel-wise class-specific loss adaptation (PCLA). First, the class-wise gradient magnitude homogenization helps alleviate the imbalance among label masks by ensuring equal consideration of the class-wise impact on model updates. Second, PCLA tackles the detrimental impact of both rare classes within the long-tailed distribution and inaccurate predictions from previous training stages by encouraging learning classes with low prediction confidence and guarding against forgetting classes with high confidence. This combined approach fosters robust learning while preventing the model from forgetting previously learned knowledge. PAT exhibits significant performance improvements, surpassing the current state-of-the-art by 2.2% in the NyU dataset. Moreover, it enhances overall pixel-wise accuracy by 2.85% and intersection over union value by 2.07%, with a particularly notable declination of 0.39% in detecting rare classes compared to Balance Logits Variation, as demonstrated on the three popular datasets, i.e., OxfordPetIII, CityScape, and NYU.

cs.CV↗

arXiv2024

TrAISformer -- A Transformer Network with Sparse Augmented Data Representation and Cross Entropy Loss for AIS-based Vessel Trajectory Prediction

Vessel trajectory prediction plays a pivotal role in numerous maritime applications and services. While the Automatic Identification System (AIS) offers a rich source of information to address this task, forecasting vessel trajectory using AIS data remains challenging, even for modern machine learning techniques, because of the inherent heterogeneous and multimodal nature of motion data. In this paper, we propose a novel approach to tackle these challenges. We introduce a discrete, high-dimensional representation of AIS data and a new loss function designed to explicitly address heterogeneity and multimodality. The proposed model-referred to as TrAISformer-is a modified transformer network that extracts long-term temporal patterns in AIS vessel trajectories in the proposed enriched space to forecast the positions of vessels several hours ahead. We report experimental results on real, publicly available AIS data. TrAISformer significantly outperforms state-of-the-art methods, with an average prediction performance below 10 nautical miles up to ~10 hours.

cs.AI↗

arXiv2023

Social Optimum Equilibrium Selection for Distributed Multi-Agent Optimization

We study the open question of how players learn to play a social optimum pure-strategy Nash equilibrium (PSNE) through repeated interactions in general-sum coordination games. A social optimum of a game is the stable Pareto-optimal state that provides a maximum return in the sum of all players' payoffs (social welfare) and always exists. We consider finite repeated games where each player only has access to its own utility (or payoff) function but is able to exchange information with other players. We develop a novel regret matching (RM) based algorithm for computing an efficient PSNE solution that could approach a desired Pareto-optimal outcome yielding the highest social welfare among all the attainable equilibria in the long run. Our proposed learning procedure follows the regret minimization framework but extends it in three major ways: (1) agents use global, instead of local, utility for calculating regrets, (2) each agent maintains a small and diminishing exploration probability in order to explore various PSNEs, and (3) agents stay with the actions that achieve the best global utility thus far, regardless of regrets. We prove that these three extensions enable the algorithm to select the stable social optimum equilibrium instead of converging to an arbitrary or cyclic equilibrium as in the conventional RM approach. We demonstrate the effectiveness of our approach through a set of applications in multi-agent distributed control, including a large-scale resource allocation game and a hard combinatorial task assignment problem for which no efficient (polynomial) solution exists.

cs.GT↗

arXiv2023

Bayesian Rationality in Satisfaction Games

We introduce a new paradigm for game theory -- Bayesian satisfaction. This novel approach is a synthesis of the idea of Bayesian rationality introduced by Aumann, and satisfaction games. The concept of Bayesian rationality for which, in part, Robert Aumann was awarded the Nobel Prize in 2005, is concerned with players in a game acting in their own best interest given a subjective knowledge of the other players' behaviours as represented by a probability distribution. Satisfaction games have emerged in the engineering literature as a way of modelling competitive interactions in resource allocation problems where players seek to attain a specified level of utility, rather than trying to maximise utility. In this paper, we explore the relationship between optimality in Aumann's sense (correlated equilibria), and satisfaction in games. We show that correlated equilibria in a satisfaction game represent stable outcomes in which no player can increase their probability of satisfaction by unilateral deviation from the specified behaviour. Thus, we propose a whole new class of equilibrium outcomes in satisfaction games which include existing notions of equilibria in such games. Iterative algorithms for computing such equilibria based on the existing ideas of regret matching are presented and interpreted within the satisfaction framework. Numerical examples of resource allocation are presented to illustrate the behaviour of these algorithms. A notable feature of these algorithms is that they almost always find equilibrium outcomes whereas existing approaches in satisfaction games may not.

cs.GT↗

arXiv2022

Technical Report: Using Static Analysis to Compute Benefit of Tolerating Consistency

Synchronization is the Achilles heel of concurrent programs. Synchronization requirement is often used to ensure that the execution of the concurrent program can be serialized. Without synchronization requirement, a program suffers from consistency violations. Recently, it was shown that if programs are designed to tolerate such consistency violation faults (\cvf{s}) then one can obtain substantial performance gain. Previous efforts to analyze the effect of \cvf-tolerance are limited to run-time analysis of the program to determine if tolerating \cvf{s} can improve the performance. Such run-time analysis is very expensive and provides limited insight. In this work, we consider the question, `Can static analysis of the program predict the benefit of \cvf-tolerance?' We find that the answer to this question is affirmative. Specifically, we use static analysis to evaluate the cost of a \cvf and demonstrate that it can be used to predict the benefit of \cvf-tolerance. We also find that when faced with a large state space, partial analysis of the state space (via sampling) also provides the required information to predict the benefit of \cvf-tolerance. Furthermore, we observe that the \cvf-cost distribution is exponential in nature, i.e., the probability that a \cvf has a cost of $c$ is $A.B^{-c}$, where $A$ and $B$ are constants, i.e., most \cvf{s} cause no/low perturbation whereas a small number of \cvf{s} cause a large perturbation. This opens up new aveneus to evaluate the benefit of \cvf-tolerance.

cs.DC↗

arXiv2022

Impact of the Consistency Model on Checkpointing of Distributed Shared Memory

In this report, we consider the impact of the consistency model on checkpointing and rollback algorithms for distributed shared memory. In particular, we consider specific implementations of four consistency models for distributed shared memory, namely, linearizability, sequential consistency, causal consistency and eventual consistency, and develop checkpointing and rollback algorithms that can be integrated into the implementations of the consistency models. Our results empirically demonstrate that the mechanisms used to implement stronger consistency models lead to simpler or more efficient checkpointing algorithms.

cs.DC↗