arXiv subjects

Danh Le-Phuoc

Publications and source records attributed to Danh Le-Phuoc.

At least 19 recordsLinked to original sources

arXiv2026

CQELS-TrieGS Report: Snapshot-Consistent Constant-Delay Enumeration for Streaming Graph Queries

Continuous graph-query engines must process edge updates while making current query results available to concurrent consumers. Existing dynamic constant-delay enumeration methods provide strong per-answer delay guarantees, but are commonly formulated as a maintenance-then-enumeration process. Conversely, multicore graph-stream engines emphasize update throughput and match discovery without a query-level snapshot guarantee for concurrent full-result enumeration. We present TrieGS, a shared-memory engine that maintains a query-specific CDE state over a streaming graph. Logically, TrieGS uses the classical free-connex witness-subtree enumerator; dynamically, it maintains multiplicity payloads using exact signed deltas; physically, RDF terms are dictionary-encoded and the required access structures are realized as versioned LFNT relations (Lock-Free Nested Trie). The new systems problem is not relation-level snapshotting alone: an enumeration job must observe one consistent state across all interdependent base relations, projections, views, and indexes. TrieGS therefore publishes an atomic root vector only after an update epoch has fully propagated. Enumeration threads pin one published root vector and traverse immutable versions while later updates continue.

cs.DB↗

arXiv2026

When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Federated Class-Incremental Learning

Federated class-incremental learning (FCIL) becomes substantially harder when clients observe different label subsets, progress through tasks at different stages, and provide uneven supervision for the same semantic concepts. Existing FCIL methods often preserve old knowledge through input-space synthesis, but they can be fragile under heterogeneous task streams and difficult to transfer across modalities. To alleviate such issues, we propose PRO, a framework that replaces synthetic input replay with projected rehearsal orchestration. To remove external pretraining, we evaluate all methods under the same warmup. After this, PRO maintains compact class-level projected memories on the server and allows clients perform balanced pseudo multi-task training over current examples and old projected memories. To handle stronger representation drift, we further introduce PRO-MAX, which augments PRO with neighborhood-weighted memory alignment while preserving the same server-light principle that the server only aggregates model updates and memory statistics. Across image, text, and graph benchmarks, PRO and PRO-MAX improve retention and final utility under heterogeneous streams while remaining competitive in homogeneous FCIL. Even when baselines are given expanded replay budgets, they degrade under supervision imbalance and stage misalignment, indicating that replay quantity alone does not resolve replay-quality failures. Additional weak-task diagnostics further show that larger replay mismatch is associated with larger downstream degradation, while our method keeps projected memories better aligned with the evolving representation.

cs.LG↗

arXiv2026

Efficiently Assemble Normalization Layers and Regularization for Federated Domain Generalization

Domain shift is a formidable issue in Machine Learning that causes a model to suffer from performance degradation when tested on unseen domains. Federated Domain Generalization (FedDG) attempts to train a global model using collaborative clients in a privacy-preserving manner that can generalize well to unseen clients possibly with domain shift. However, most existing FedDG methods either cause additional privacy risks of data leakage or induce significant costs in client communication and computation, which are major concerns in the Federated Learning paradigm. To circumvent these challenges, here we introduce a novel architectural method for FedDG, namely gPerXAN, which relies on a normalization scheme working with a guiding regularizer. In particular, we carefully design Personalized eXplicitly Assembled Normalization to enforce client models selectively filtering domain-specific features that are biased towards local data while retaining discrimination of those features. Then, we incorporate a simple yet effective regularizer to guide these models in directly capturing domain-invariant representations that the global model's classifier can leverage. Extensive experimental results on two benchmark datasets, i.e., PACS and Office-Home, and a real-world medical dataset, Camelyon17, indicate that our proposed method outperforms other existing methods in addressing this particular problem.

cs.CV↗

arXiv2025

Edge-Based Predictive Data Reduction for Smart Agriculture: A Lightweight Approach to Efficient IoT Communication

The rapid growth of IoT devices has led to an enormous amount of sensor data that requires transmission to cloud servers for processing, resulting in excessive network congestion, increased latency and high energy consumption. This is particularly problematic in resource-constrained and remote environments where bandwidth is limited, and battery-dependent devices further emphasize the problem. Moreover, in domains such as agriculture, consecutive sensor readings often have minimal variation, making continuous data transmission inefficient and unnecessarily resource intensive. To overcome these challenges, we propose an analytical prediction algorithm designed for edge computing environments and validated through simulation. The proposed solution utilizes a predictive filter at the network edge that forecasts the next sensor data point and triggers data transmission only when the deviation from the predicted value exceeds a predefined tolerance. A complementary cloud-based model ensures data integrity and overall system consistency. This dual-model strategy effectively reduces communication overhead and demonstrates potential for improving energy efficiency by minimizing redundant transmissions. In addition to reducing communication load, our approach leverages both in situ and satellite observations from the same locations to enhance model robustness. It also supports cross-site generalization, enabling models trained in one region to be effectively deployed elsewhere without retraining. This makes our solution highly scalable, energy-aware, and well-suited for optimizing sensor data transmission in remote and bandwidth-constrained IoT environments.

cs.LG↗

arXiv2025

SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts--Extended Version

Small Language Models (SLMs) offer computational efficiency and accessibility, yet a systematic evaluation of their performance and environmental impact remains lacking. We introduce SLM-Bench, the first benchmark specifically designed to assess SLMs across multiple dimensions, including accuracy, computational efficiency, and sustainability metrics. SLM-Bench evaluates 15 SLMs on 9 NLP tasks using 23 datasets spanning 14 domains. The evaluation is conducted on 4 hardware configurations, providing a rigorous comparison of their effectiveness. Unlike prior benchmarks, SLM-Bench quantifies 11 metrics across correctness, computation, and consumption, enabling a holistic assessment of efficiency trade-offs. Our evaluation considers controlled hardware conditions, ensuring fair comparisons across models. We develop an open-source benchmarking pipeline with standardized evaluation protocols to facilitate reproducibility and further research. Our findings highlight the diverse trade-offs among SLMs, where some models excel in accuracy while others achieve superior energy efficiency. SLM-Bench sets a new standard for SLM evaluation, bridging the gap between resource efficiency and real-world applicability.

cs.CL↗

arXiv2025

Cooperative Students: Navigating Unsupervised Domain Adaptation in Nighttime Object Detection

Unsupervised Domain Adaptation (UDA) has shown significant advancements in object detection under well-lit conditions; however, its performance degrades notably in low-visibility scenarios, especially at night, posing challenges not only for its adaptability in low signal-to-noise ratio (SNR) conditions but also for the reliability and efficiency of automated vehicles. To address this problem, we propose a \textbf{Co}operative \textbf{S}tudents (\textbf{CoS}) framework that innovatively employs global-local transformations (GLT) and a proxy-based target consistency (PTC) mechanism to capture the spatial consistency in day- and night-time scenarios effectively, and thus bridge the significant domain shift across contexts. Building upon this, we further devise an adaptive IoU-informed thresholding (AIT) module to gradually avoid overlooking potential true positives and enrich the latent information in the target domain. Comprehensive experiments show that CoS essentially enhanced UDA performance in low-visibility conditions and surpasses current state-of-the-art techniques, achieving an increase in mAP of 3.0\%, 1.9\%, and 2.5\% on BDD100K, SHIFT, and ACDC datasets, respectively. Code is available at https://github.com/jichengyuan/Cooperitive_Students.

cs.CV↗

arXiv2024

Towards an Implementation of the Knowledge-Based Control Plane for Intelligent Swarm Networks

This paper proposes the possibility of integrating Dynamic Knowledge Graph (DKG) with Software-Defined Networking (SDN). This new approach aims to assist the management and control capabilities of the swarm network. The DKG works as a unified network data view, capturing network information such as topology, flow rules, host information, switch information, link status, and in-band network telemetry (INT) data. Benefited from the deep programmability of SDN, the network information can be converted into RDF format constantly, and the DKG will be dynamically updated. This approach helps the network operators to control their network infrastructure, such as allocating resource effectively and decision making at the application layer. Potential use cases demonstrate the applicability and advantages of the proposed approach. Examples include access control in swarm network scenarios and applying adaptive routing strategies, etc. These use cases illustrate how DKG-based SDN can address swarm network management challenges effectively, optimizing performance and resource utilization.

cs.NI↗

arXiv2024

Co-Learning: Towards Semi-Supervised Object Detection with Road-side Cameras

Recently, deep learning has experienced rapid expansion, contributing significantly to the progress of supervised learning methodologies. However, acquiring labeled data in real-world settings can be costly, labor-intensive, and sometimes scarce. This challenge inhibits the extensive use of neural networks for practical tasks due to the impractical nature of labeling vast datasets for every individual application. To tackle this, semi-supervised learning (SSL) offers a promising solution by using both labeled and unlabeled data to train object detectors, potentially enhancing detection efficacy and reducing annotation costs. Nevertheless, SSL faces several challenges, including pseudo-target inconsistencies, disharmony between classification and regression tasks, and efficient use of abundant unlabeled data, especially on edge devices, such as roadside cameras. Thus, we developed a teacher-student-based SSL framework, Co-Learning, which employs mutual learning and annotation-alignment strategies to adeptly navigate these complexities and achieves comparable performance as fully-supervised solutions using 10\% labeled data.

cs.CV↗

arXiv2024

A comparison of extended object tracking with multi-modal sensors in indoor environment

This paper presents a preliminary study of an efficient object tracking approach, comparing the performance of two different 3D point cloud sensory sources: LiDAR and stereo cameras, which have significant price differences. In this preliminary work, we focus on single object tracking. We first developed a fast heuristic object detector that utilizes prior information about the environment and target. The resulting target points are subsequently fed into an extended object tracking framework, where the target shape is parameterized using a star-convex hypersurface model. Experimental results show that our object tracking method using a stereo camera achieves performance similar to that of a LiDAR sensor, with a cost difference of more than tenfold.

cs.RO↗

arXiv2024

Experimental comparison of graph-based approximate nearest neighbor search algorithms on edge devices

In this paper, we present an experimental comparison of various graph-based approximate nearest neighbor (ANN) search algorithms deployed on edge devices for real-time nearest neighbor search applications, such as smart city infrastructure and autonomous vehicles. To the best of our knowledge, this specific comparative analysis has not been previously conducted. While existing research has explored graph-based ANN algorithms, it has often been limited to single-threaded implementations on standard commodity hardware. Our study leverages the full computational and storage capabilities of edge devices, incorporating additional metrics such as insertion and deletion latency of new vectors and power consumption. This comprehensive evaluation aims to provide valuable insights into the performance and suitability of these algorithms for edge-based real-time tracking systems enhanced by nearest-neighbor search algorithms.

cs.DS↗

arXiv2024

Reducing Communication Overhead in the IoT-Edge-Cloud Continuum: A Survey on Protocols and Data Reduction Strategies

The adoption of the Internet of Things (IoT) deployments has led to a sharp increase in network traffic as a vast number of IoT devices communicate with each other and IoT services through the IoT-edge-cloud continuum. This network traffic increase poses a major challenge to the global communications infrastructure since it hinders communication performance and also puts significant strain on the energy consumption of IoT devices. To address these issues, efficient and collaborative IoT solutions which enable information exchange while reducing the transmitted data and associated network traffic are crucial. This survey provides a comprehensive overview of the communication technologies and protocols as well as data reduction strategies that contribute to this goal. First, we present a comparative analysis of prevalent communication technologies in the IoT domain, highlighting their unique characteristics and exploring the potential for protocol composition and joint usage to enhance overall communication efficiency within the IoT-edge-cloud continuum. Next, we investigate various data traffic reduction techniques tailored to the IoT-edge-cloud context and evaluate their applicability and effectiveness on resource-constrained and devices. Finally, we investigate the emerging concepts that have the potential to further reduce the communication overhead in the IoT-edge-cloud continuum, including cross-layer optimization strategies and Edge AI techniques for IoT data reduction. The paper offers a comprehensive roadmap for developing efficient and scalable solutions across the layers of the IoT-edge-cloud continuum that are beneficial for real-time processing to alleviate network congestion in complex IoT environments.

cs.NI↗

arXiv2024

Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator

Federated Class-Incremental Learning (FCIL) increasingly becomes important in the decentralized setting, where it enables multiple participants to collaboratively train a global model to perform well on a sequence of tasks without sharing their private data. In FCIL, conventional Federated Learning algorithms such as FedAVG often suffer from catastrophic forgetting, resulting in significant performance declines on earlier tasks. Recent works, based on generative models, produce synthetic images to help mitigate this issue across all classes, but these approaches' testing accuracy on previous classes is still much lower than recent classes, i.e., having better plasticity than stability. To overcome these issues, this paper presents Federated Global Twin Generator (FedGTG), an FCIL framework that exploits privacy-preserving generative-model training on the global side without accessing client data. Specifically, the server trains a data generator and a feature generator to create two types of information from all seen classes, and then it sends the synthetic data to the client side. The clients then use feature-direction-controlling losses to make the local models retain knowledge and learn new tasks well. We extensively analyze the robustness of FedGTG on natural images, as well as its ability to converge to flat local minima and achieve better-predicting confidence (calibration). Experimental results on CIFAR-10, CIFAR-100, and tiny-ImageNet demonstrate the improvements in accuracy and forgetting measures of FedGTG compared to previous frameworks.

cs.LG↗

arXiv2024

Exploring the Practicality of Federated Learning: A Survey Towards the Communication Perspective

Federated Learning (FL) is a promising paradigm that offers significant advancements in privacy-preserving, decentralized machine learning by enabling collaborative training of models across distributed devices without centralizing data. However, the practical deployment of FL systems faces a significant bottleneck: the communication overhead caused by frequently exchanging large model updates between numerous devices and a central server. This communication inefficiency can hinder training speed, model performance, and the overall feasibility of real-world FL applications. In this survey, we investigate various strategies and advancements made in communication-efficient FL, highlighting their impact and potential to overcome the communication challenges inherent in FL systems. Specifically, we define measures for communication efficiency, analyze sources of communication inefficiency in FL systems, and provide a taxonomy and comprehensive review of state-of-the-art communication-efficient FL methods. Additionally, we discuss promising future research directions for enhancing the communication efficiency of FL systems. By addressing the communication bottleneck, FL can be effectively applied and enable scalable and practical deployment across diverse applications that require privacy-preserving, decentralized machine learning, such as IoT, healthcare, or finance.

cs.LG↗

arXiv2024

VisionKG: Unleashing the Power of Visual Datasets via Knowledge Graph

The availability of vast amounts of visual data with heterogeneous features is a key factor for developing, testing, and benchmarking of new computer vision (CV) algorithms and architectures. Most visual datasets are created and curated for specific tasks or with limited image data distribution for very specific situations, and there is no unified approach to manage and access them across diverse sources, tasks, and taxonomies. This not only creates unnecessary overheads when building robust visual recognition systems, but also introduces biases into learning systems and limits the capabilities of data-centric AI. To address these problems, we propose the Vision Knowledge Graph (VisionKG), a novel resource that interlinks, organizes and manages visual datasets via knowledge graphs and Semantic Web technologies. It can serve as a unified framework facilitating simple access and querying of state-of-the-art visual datasets, regardless of their heterogeneous formats and taxonomies. One of the key differences between our approach and existing methods is that ours is knowledge-based rather than metadatabased. It enhances the enrichment of the semantics at both image and instance levels and offers various data retrieval and exploratory services via SPARQL. VisionKG currently contains 519 million RDF triples that describe approximately 40 million entities, and are accessible at https://vision.semkg.org and through APIs. With the integration of 30 datasets and four popular CV tasks, we demonstrate its usefulness across various scenarios when working with CV pipelines.

cs.CV↗

arXiv2023

Semantic Programming for Device-Edge-Cloud Continuum

This position paper presents ThothSP, a Semantic Programming framework with the aim of lowering the coding effort in building smart applications on the Device-Edge-Cloud continuum by leveraging semantic knowledge. It introduces a novel neural-symbolic stream fusion mechanism, which enables the specification of data fusion pipelines via declarative rules, with degrees of learnable probabilistic weights. Moreover, it includes an adaptive federator that allows the Thoth>runtime to be distributed across multiple compute nodes in a network, and to coordinate their resources to collaboratively process tasks by delegating partial workloads to their peers. To demonstrate ThothSP's capability, we report a case study on a distributed camera network to show ThothSP's behaviour against a traditional edge-cloud setup.

cs.DC↗

arXiv2023

Building a P2P RDF Store for Edge Devices

The Semantic Web technologies have been used in the Internet of Things (IoT) to facilitate data interoperability and address data heterogeneity issues. The Resource Description Framework (RDF) model is employed in the integration of IoT data, with RDF engines serving as gateways for semantic integration. However, storing and querying RDF data obtained from distributed sources across a dynamic network of edge devices presents a challenging task. The distributed nature of the edge shares similarities with Peer-to-Peer (P2P) systems. These similarities include attributes like node heterogeneity, limited availability, and resources. The nodes primarily undertake tasks related to data storage and processing. Therefore, the P2P models appear to present an attractive approach for constructing distributed RDF stores. Based on P-Grid, a data indexing mechanism for load balancing and range query processing in P2P systems, this paper proposes a design for storing and sharing RDF data on P2P networks of low-cost edge devices. Our design aims to integrate both P-Grid and an edge-based RDF storage solution, RDF4Led for building an P2P RDF engine. This integration can maintain RDF data access and query processing while scaling with increasing data and network size. We demonstrated the scaling behavior of our implementation on a P2P network, involving up to 16 nodes of Raspberry Pi 4 devices.

cs.DB↗

arXiv2023

Temporal Saliency Detection Towards Explainable Transformer-based Timeseries Forecasting

Despite the notable advancements in numerous Transformer-based models, the task of long multi-horizon time series forecasting remains a persistent challenge, especially towards explainability. Focusing on commonly used saliency maps in explaining DNN in general, our quest is to build attention-based architecture that can automatically encode saliency-related temporal patterns by establishing connections with appropriate attention heads. Hence, this paper introduces Temporal Saliency Detection (TSD), an effective approach that builds upon the attention mechanism and applies it to multi-horizon time series prediction. While our proposed architecture adheres to the general encoder-decoder structure, it undergoes a significant renovation in the encoder component, wherein we incorporate a series of information contracting and expanding blocks inspired by the U-Net style architecture. The TSD approach facilitates the multiresolution analysis of saliency patterns by condensing multi-heads, thereby progressively enhancing the forecasting of complex time series data. Empirical evaluations illustrate the superiority of our proposed approach compared to other models across multiple standard benchmark datasets in diverse far-horizon forecasting settings. The initial TSD achieves substantial relative improvements of 31% and 46% over several models in the context of multivariate and univariate prediction. We believe the comprehensive investigations presented in this study will offer valuable insights and benefits to future research endeavors.

cs.LG↗

arXiv2023

An Empirical Study of Federated Learning on IoT-Edge Devices: Resource Allocation and Heterogeneity

Nowadays, billions of phones, IoT and edge devices around the world generate data continuously, enabling many Machine Learning (ML)-based products and applications. However, due to increasing privacy concerns and regulations, these data tend to reside on devices (clients) instead of being centralized for performing traditional ML model training. Federated Learning (FL) is a distributed approach in which a single server and multiple clients collaboratively build an ML model without moving data away from clients. Whereas existing studies on FL have their own experimental evaluations, most experiments were conducted using a simulation setting or a small-scale testbed. This might limit the understanding of FL implementation in realistic environments. In this empirical study, we systematically conduct extensive experiments on a large network of IoT and edge devices (called IoT-Edge devices) to present FL real-world characteristics, including learning performance and operation (computation and communication) costs. Moreover, we mainly concentrate on heterogeneous scenarios, which is the most challenging issue of FL. By investigating the feasibility of on-device implementation, our study provides valuable insights for researchers and practitioners, promoting the practicality of FL and assisting in improving the current design of real FL systems.

cs.LG↗