Abstract:In prototype-based federated learning, the exchange of model parameters between clients and the master server is replaced by transmission of prototypes or quantized versions of the data samples to the aggregation server. A fully decentralized deployment of prototype-based learning, without a central agregartor of prototypes, is more robust upon network failures and reacts faster to changes in the statistical distribution of the data, suggesting potential advantages and quick adaptation in dynamic learning tasks, e.g., when the data sources are IoT devices or when data is non-iid. In this paper, we consider the problem of designing a communication-efficient decentralized learning system based on prototypes. We address the challenge of prototype redundancy by leveraging on a twofold data compression technique, i.e., sending only update messages if the prototypes are informationtheoretically useful (via the Jensen-Shannon distance), and using clustering on the prototypes to compress the update messages used in the gossip protocol. We also use parallel instead of sequential gossiping, and present an analysis of its age-of-information (AoI). Our experimental results show that, with these improvements, the communications load can be substantially reduced without decreasing the convergence rate of the learning algorithm.
Abstract:Federated Learning (FL) emerges as a distributed machine learning approach that addresses privacy concerns by training AI models locally on devices. Decentralized Federated Learning (DFL) extends the FL paradigm by eliminating the central server, thereby enhancing scalability and robustness through the avoidance of a single point of failure. However, DFL faces significant challenges in optimizing security, as most Byzantine-robust algorithms proposed in the literature are designed for centralized scenarios. In this paper, we present a novel Byzantine-robust aggregation algorithm to enhance the security of Decentralized Federated Learning environments, coined WFAgg. This proposal handles the adverse conditions and strength robustness of dynamic decentralized topologies at the same time by employing multiple filters to identify and mitigate Byzantine attacks. Experimental results demonstrate the effectiveness of the proposed algorithm in maintaining model accuracy and convergence in the presence of various Byzantine attack scenarios, outperforming state-of-the-art centralized Byzantine-robust aggregation schemes (such as Multi-Krum or Clustering). These algorithms are evaluated on an IID image classification problem in both centralized and decentralized scenarios.
Abstract:Continual learning (CL) poses the important challenge of adapting to evolving data distributions without forgetting previously acquired knowledge while consolidating new knowledge. In this paper, we introduce a new methodology, coined as Tabular-data Rehearsal-based Incremental Lifelong Learning framework (TRIL3), designed to address the phenomenon of catastrophic forgetting in tabular data classification problems. TRIL3 uses the prototype-based incremental generative model XuILVQ to generate synthetic data to preserve old knowledge and the DNDF algorithm, which was modified to run in an incremental way, to learn classification tasks for tabular data, without storing old samples. After different tests to obtain the adequate percentage of synthetic data and to compare TRIL3 with other CL available proposals, we can conclude that the performance of TRIL3 outstands other options in the literature using only 50% of synthetic data.
Abstract:Decentralised machine learning has recently been proposed as a potential solution to the security issues of the canonical federated learning approach. In this paper, we propose a decentralised and collaborative machine learning framework specially oriented to resource-constrained devices, usual in IoT deployments. With this aim we propose the following construction blocks. First, an incremental learning algorithm based on prototypes that was specifically implemented to work in low-performance computing elements. Second, two random-based protocols to exchange the local models among the computing elements in the network. Finally, two algorithmics approaches for prediction and prototype creation. This proposal was compared to a typical centralized incremental learning approach in terms of accuracy, training time and robustness with very promising results.
Abstract:This paper introduces a complete method for the automatic detection, identification and localization of lighting elements in buildings, leveraging the available building information modeling (BIM) data of a building and feeding the BIM model with the new collected information, which is key for energy-saving strategies. The detection system is heavily improved from our previous work, with the following two main contributions: (i) a new refinement algorithm to provide a better detection rate and identification performance with comparable computational resources and (ii) a new plane estimation, filtering and projection step to leverage the BIM information earlier for lamps that are both hanging and embedded. The two modifications are thoroughly tested in five different case studies, yielding better results in terms of detection, identification and localization.
Abstract:Computer vision is used in this work to detect lighting elements in buildings with the goal of improving the accuracy of previous methods to provide a precise inventory of the location and state of lamps. Using the framework developed in our previous works, we introduce two new modifications to enhance the system: first, a constraint on the orientation of the detected poses in the optimization methods for both the initial and the refined estimates based on the geometric information of the building information modelling (BIM) model; second, an additional reprojection error filtering step to discard the erroneous poses introduced with the orientation restrictions, keeping the identification and localization errors low while greatly increasing the number of detections. These~enhancements are tested in five different case studies with more than 30,000 images, with results showing improvements in the number of detections, the percentage of correct model and state identifications, and the distance between detections and reference positions
Abstract:Citizens are actively interacting with their surroundings, especially through social media. Not only do shared posts give important information about what is happening (from the users' perspective), but also the metadata linked to these posts offer relevant data, such as the GPS-location in Location-based Social Networks (LBSNs). In this paper we introduce a global analysis of the geo-tagged posts in social media which supports (i) the detection of unexpected behavior in the city and (ii) the analysis of the posts to infer what is happening. The former is obtained by applying density-based clustering techniques, whereas the latter is consequence of applying natural language processing. We have applied our methodology to a dataset obtained from Instagram activity in New York City for seven months obtaining promising results. The developed algorithms require very low resources, being able to analyze millions of data-points in commodity hardware in less than one hour without applying complex parallelization techniques. Furthermore, the solution can be easily adapted to other geo-tagged data sources without extra effort.
Abstract:Undoubtedly, Location-based Social Networks (LBSNs) provide an interesting source of geo-located data that we have previously used to obtain patterns of the dynamics of crowds throughout urban areas. According to our previous results, activity in LBSNs reflects the real activity in the city. Therefore, unexpected behaviors in the social media activity are a trustful evidence of unexpected changes of the activity in the city. In this paper we introduce a hybrid solution to early detect these changes based on applying a combination of two approaches, the use of entropy analysis and clustering techniques, on the data gathered from LBSNs. In particular, we have performed our experiments over a data set collected from Instagram for seven months in New York City, obtaining promising results.
Abstract:Recently, Deep Learning (DL) approaches have been applied to solve the Sentiment Classification (SC) problem, which is a core task in reviews mining or Sentiment Analysis (SA). The performances of these approaches are affected by different factors. This paper addresses these factors and classifies them into three categories: data preparation based factors, feature representation based factors and the classification techniques based factors. The paper is a comprehensive literature-based survey that compares the performance of more than 100 DL-based SC approaches by using 21 public datasets of reviews given by customers within three specific application domains (products, movies and restaurants). These 21 datasets have different characteristics (balanced/imbalanced, size, etc.) to give a global vision for our study. The comparison explains how the proposed factors quantitatively affect the performance of the studied DL-based SC approaches.
Abstract:E-Commerce (EC) websites provide a large amount of useful information that exceed human cognitive processing ability. In order to help customers in comparing alternatives when buying a product, previous studies designed opinion summarization systems based on customer reviews. They ignored templates' information provided by manufacturers, although these descriptive information have much product aspects or characteristics. Therefore, this paper proposes a methodology coined as SEOpinion (Summa-rization and Exploration of Opinions) which provides a summary for the product aspects and spots opinion(s) regarding them, using a combination of templates' information with the customer reviews in two main phases. First, the Hierarchical Aspect Extraction (HAE) phase creates a hierarchy of product aspects from the template. Subsequently, the Hierarchical Aspect-based Opinion Summarization (HAOS) phase enriches this hierarchy with customers' opinions; to be shown to other potential buyers. To test the feasibility of using Deep Learning-based BERT techniques with our approach, we have created a corpus by gathering information from the top five EC websites for laptops. The experimental results show that Recurrent Neural Network (RNN) achieves better results (77.4% and 82.6% in terms of F1-measure for the first and second phase) than the Convolutional Neural Network (CNN) and the Support Vector Machine (SVM) technique.