arXiv subjects

Xavier Franch

Publications and source records attributed to Xavier Franch.

At least 37 records · Page 2Linked to original sources

arXiv2025

Leveraging Encoder-only Large Language Models for Mobile App Review Feature Extraction

Mobile app review analysis presents unique challenges due to the low quality, subjective bias, and noisy content of user-generated documents. Extracting features from these reviews is essential for tasks such as feature prioritization and sentiment analysis, but it remains a challenging task. Meanwhile, encoder-only models based on the Transformer architecture have shown promising results for classification and information extraction tasks for multiple software engineering processes. This study explores the hypothesis that encoder-only large language models can enhance feature extraction from mobile app reviews. By leveraging crowdsourced annotations from an industrial context, we redefine feature extraction as a supervised token classification task. Our approach includes extending the pre-training of these models with a large corpus of user reviews to improve contextual understanding and employing instance selection techniques to optimize model fine-tuning. Empirical evaluations demonstrate that this method improves the precision and recall of extracted features and enhances performance efficiency. Key contributions include a novel approach to feature extraction, annotated datasets, extended pre-trained models, and an instance selection mechanism for cost-effective fine-tuning. This research provides practical methods and empirical evidence in applying large language models to natural language processing tasks within mobile app reviews, offering improved performance in feature extraction.

cs.CL↗

arXiv2025

Addressing Quality Challenges in Deep Learning: The Role of MLOps and Domain Knowledge

Deep learning (DL) systems present unique challenges in software engineering, especially concerning quality attributes like correctness and resource efficiency. While DL models excel in specific tasks, engineering DL systems is still essential. The effort, cost, and potential diminishing returns of continual improvements must be carefully evaluated, as software engineers often face the critical decision of when to stop refining a system relative to its quality attributes. This experience paper explores the role of MLOps practices -- such as monitoring and experiment tracking -- in creating transparent and reproducible experimentation environments that enable teams to assess and justify the impact of design decisions on quality attributes. Furthermore, we report on experiences addressing the quality challenges by embedding domain knowledge into the design of a DL model and its integration within a larger system. The findings offer actionable insights into the benefits of domain knowledge and MLOps and the strategic consideration of when to limit further optimizations in DL projects to maximize overall system quality and reliability.

cs.SE↗

arXiv2024

A Framework for Using LLMs for Repository Mining Studies in Empirical Software Engineering

Context: The emergence of Large Language Models (LLMs) has significantly transformed Software Engineering (SE) by providing innovative methods for analyzing software repositories. Objectives: Our objective is to establish a practical framework for future SE researchers needing to enhance the data collection and dataset while conducting software repository mining studies using LLMs. Method: This experience report shares insights from two previous repository mining studies, focusing on the methodologies used for creating, refining, and validating prompts that enhance the output of LLMs, particularly in the context of data collection in empirical studies. Results: Our research packages a framework, coined Prompt Refinement and Insights for Mining Empirical Software repositories (PRIMES), consisting of a checklist that can improve LLM usage performance, enhance output quality, and minimize errors through iterative processes and comparisons among different LLMs. We also emphasize the significance of reproducibility by implementing mechanisms for tracking model results. Conclusion: Our findings indicate that standardizing prompt engineering and using PRIMES can enhance the reliability and reproducibility of studies utilizing LLMs. Ultimately, this work calls for further research to address challenges like hallucinations, model biases, and cost-effectiveness in integrating LLMs into workflows.

cs.SE↗

arXiv2024

Towards a Classification of Open-Source ML Models and Datasets for Software Engineering

Background: Open-Source Pre-Trained Models (PTMs) and datasets provide extensive resources for various Machine Learning (ML) tasks, yet these resources lack a classification tailored to Software Engineering (SE) needs. Aims: We apply an SE-oriented classification to PTMs and datasets on a popular open-source ML repository, Hugging Face (HF), and analyze the evolution of PTMs over time. Method: We conducted a repository mining study. We started with a systematically gathered database of PTMs and datasets from the HF API. Our selection was refined by analyzing model and dataset cards and metadata, such as tags, and confirming SE relevance using Gemini 1.5 Pro. All analyses are replicable, with a publicly accessible replication package. Results: The most common SE task among PTMs and datasets is code generation, with a primary focus on software development and limited attention to software management. Popular PTMs and datasets mainly target software development. Among ML tasks, text generation is the most common in SE PTMs and datasets. There has been a marked increase in PTMs for SE since 2023 Q2. Conclusions: This study underscores the need for broader task coverage to enhance the integration of ML within SE practices.

cs.SE↗

arXiv2024

Impact of ML Optimization Tactics on Greener Pre-Trained ML Models

Background: Given the fast-paced nature of today's technology, which has surpassed human performance in tasks like image classification, visual reasoning, and English understanding, assessing the impact of Machine Learning (ML) on energy consumption is crucial. Traditionally, ML projects have prioritized accuracy over energy, creating a gap in energy consumption during model inference. Aims: This study aims to (i) analyze image classification datasets and pre-trained models, (ii) improve inference efficiency by comparing optimized and non-optimized models, and (iii) assess the economic impact of the optimizations. Method: We conduct a controlled experiment to evaluate the impact of various PyTorch optimization techniques (dynamic quantization, torch.compile, local pruning, and global pruning) to 42 Hugging Face models for image classification. The metrics examined include GPU utilization, power and energy consumption, accuracy, time, computational complexity, and economic costs. The models are repeatedly evaluated to quantify the effects of these software engineering tactics. Results: Dynamic quantization demonstrates significant reductions in inference time and energy consumption, making it highly suitable for large-scale systems. Additionally, torch.compile balances accuracy and energy. In contrast, local pruning shows no positive impact on performance, and global pruning's longer optimization times significantly impact costs. Conclusions: This study highlights the role of software engineering tactics in achieving greener ML models, offering guidelines for practitioners to make informed decisions on optimization methods that align with sustainability goals.

cs.LG↗

arXiv2024

The More the Merrier? Navigating Accuracy vs. Energy Efficiency Design Trade-Offs in Ensemble Learning Systems

Background: Machine learning (ML) model composition is a popular technique to mitigate shortcomings of a single ML model and to design more effective ML-enabled systems. While ensemble learning, i.e., forwarding the same request to several models and fusing their predictions, has been studied extensively for accuracy, we have insufficient knowledge about how to design energy-efficient ensembles. Objective: We therefore analyzed three types of design decisions for ensemble learning regarding a potential trade-off between accuracy and energy consumption: a) ensemble size, i.e., the number of models in the ensemble, b) fusion methods (majority voting vs. a meta-model), and c) partitioning methods (whole-dataset vs. subset-based training). Methods: By combining four popular ML algorithms for classification in different ensembles, we conducted a full factorial experiment with 11 ensembles x 4 datasets x 2 fusion methods x 2 partitioning methods (176 combinations). For each combination, we measured accuracy (F1-score) and energy consumption in J (for both training and inference). Results: While a larger ensemble size significantly increased energy consumption (size 2 ensembles consumed 37.49% less energy than size 3 ensembles, which in turn consumed 26.96% less energy than the size 4 ensembles), it did not significantly increase accuracy. Furthermore, majority voting outperformed meta-model fusion both in terms of accuracy (Cohen's d of 0.38) and energy consumption (Cohen's d of 0.92). Lastly, subset-based training led to significantly lower energy consumption (Cohen's d of 0.91), while training on the whole dataset did not increase accuracy significantly. Conclusions: From a Green AI perspective, we recommend designing ensembles of small size (2 or maximum 3 models), using subset-based training, majority voting, and energy-efficient ML algorithms like decision trees, Naive Bayes, or KNN.

cs.LG↗

arXiv2024

Unveiling Competition Dynamics in Mobile App Markets through User Reviews

User reviews published in mobile app repositories are essential for understanding user satisfaction and engagement within a specific market segment. Manual analysis of reviews is impractical due to the large data volume, and automated analysis faces challenges like data synthesis and reporting. This complicates the task for app providers in identifying patterns and significant events, especially in assessing the influence of competitor apps. Furthermore, review-based research is mostly limited to a single app or a single app provider, excluding potential competition analysis. Consequently, there is an open research challenge in leveraging user reviews to support cross-app analysis within a specific market segment. Following a case-study research method in the microblogging app market, we introduce an automatic, novel approach to support mobile app market analysis. Our approach leverages quantitative metrics and event detection techniques based on newly published user reviews. Significant events are proactively identified and summarized by comparing metric deviations with historical baseline indicators within the lifecycle of a mobile app. Results from our case study show empirical evidence of the detection of relevant events within the selected market segment, including software- or release-based events, contextual events and the emergence of new competitors.

cs.SE↗

arXiv2024

Replication in Requirements Engineering: the NLP for RE Case

[Context]} Natural language processing (NLP) techniques have been widely applied in the requirements engineering (RE) field to support tasks such as classification and ambiguity detection. Despite its empirical vocation, RE research has given limited attention to replication of NLP for RE studies. Replication is hampered by several factors, including the context specificity of the studies, the heterogeneity of the tasks involving NLP, the tasks' inherent hairiness, and, in turn, the heterogeneous reporting structure. [Solution] To address these issues, we propose a new artifact, referred to as ID-Card, whose goal is to provide a structured summary of research papers emphasizing replication-relevant information. We construct the ID-Card through a structured, iterative process based on design science. [Results] In this paper: (i) we report on hands-on experiences of replication, (ii) we review the state-of-the-art and extract replication-relevant information, (iii) we identify, through focus groups, challenges across two typical dimensions of replication: data annotation and tool reconstruction, and (iv) we present the concept and structure of the ID-Card to mitigate the identified challenges. [Contribution] This study aims to create awareness of replication in NLP for RE. We propose an ID-Card that is intended to foster study replication, but can also be used in other contexts, e.g., for educational purposes.

cs.SE↗

arXiv2024

Lessons Learned from Mining the Hugging Face Repository

The rapidly evolving fields of Machine Learning (ML) and Artificial Intelligence have witnessed the emergence of platforms like Hugging Face (HF) as central hubs for model development and sharing. This experience report synthesizes insights from two comprehensive studies conducted on HF, focusing on carbon emissions and the evolutionary and maintenance aspects of ML models. Our objective is to provide a practical guide for future researchers embarking on mining software repository studies within the HF ecosystem to enhance the quality of these studies. We delve into the intricacies of the replication package used in our studies, highlighting the pivotal tools and methodologies that facilitated our analysis. Furthermore, we propose a nuanced stratified sampling strategy tailored for the diverse HF Hub dataset, ensuring a representative and comprehensive analytical approach. The report also introduces preliminary guidelines, transitioning from repository mining to cohort studies, to establish causality in repository mining studies, particularly within the ML model of HF context. This transition is inspired by existing frameworks and is adapted to suit the unique characteristics of the HF model ecosystem. Our report serves as a guiding framework for researchers, contributing to the responsible and sustainable advancement of ML, and fostering a deeper understanding of the broader implications of ML models.

cs.SE↗

arXiv2024

Software-Based Dialogue Systems: Survey, Taxonomy and Challenges

The use of natural language interfaces in the field of human-computer interaction is undergoing intense study through dedicated scientific and industrial research. The latest contributions in the field, including deep learning approaches like recurrent neural networks, the potential of context-aware strategies and user-centred design approaches, have brought back the attention of the community to software-based dialogue systems, generally known as conversational agents or chatbots. Nonetheless, and given the novelty of the field, a generic, context-independent overview on the current state of research of conversational agents covering all research perspectives involved is missing. Motivated by this context, this paper reports a survey of the current state of research of conversational agents through a systematic literature review of secondary studies. The conducted research is designed to develop an exhaustive perspective through a clear presentation of the aggregated knowledge published by recent literature within a variety of domains, research focuses and contexts. As a result, this research proposes a holistic taxonomy of the different dimensions involved in the conversational agents' field, which is expected to help researchers and to lay the groundwork for future research in the field of natural language interfaces.

cs.CL↗

arXiv2024

Analyzing the Evolution and Maintenance of ML Models on Hugging Face

Hugging Face (HF) has established itself as a crucial platform for the development and sharing of machine learning (ML) models. This repository mining study, which delves into more than 380,000 models using data gathered via the HF Hub API, aims to explore the community engagement, evolution, and maintenance around models hosted on HF, aspects that have yet to be comprehensively explored in the literature. We first examine the overall growth and popularity of HF, uncovering trends in ML domains, framework usage, authors grouping and the evolution of tags and datasets used. Through text analysis of model card descriptions, we also seek to identify prevalent themes and insights within the developer community. Our investigation further extends to the maintenance aspects of models, where we evaluate the maintenance status of ML models, classify commit messages into various categories (corrective, perfective, and adaptive), analyze the evolution across development stages of commits metrics and introduce a new classification system that estimates the maintenance status of models based on multiple attributes. This study aims to provide valuable insights about ML model maintenance and evolution that could inform future model development strategies on platforms like HF.

cs.SE↗

arXiv2024

Energy Consumption of Automated Program Repair

Automated program repair (APR) aims to automatize the process of repairing software bugs in order to reduce the cost of maintaining software programs. Moreover, the success (given by the accuracy metric) of APR approaches has increased in recent years. However, no previous work has considered the energy impact of repairing bugs automatically using APR. The field of green software research aims to measure the energy consumption required to develop, maintain, and use software products. This paper combines, for the first time, the APR and Green software research fields. We have as main goal to define the foundation for measuring the energy consumption of the APR activity. We measure the energy consumption of ten traditional program repair tools for Java and ten fine-tuned Large-Language Models (LLM) on source code trying to repair real bugs from Defects4J, a set of real buggy programs. The initial results from this experiment show the existing trade-off between energy consumption and the ability to correctly repair bugs: Some APR tools are capable of achieving higher accuracy by spending less energy than other tools.

cs.SE↗

arXiv2024

T-FREX: A Transformer-based Feature Extraction Method from Mobile App Reviews

Mobile app reviews are a large-scale data source for software-related knowledge generation activities, including software maintenance, evolution and feedback analysis. Effective extraction of features (i.e., functionalities or characteristics) from these reviews is key to support analysis on the acceptance of these features, identification of relevant new feature requests and prioritization of feature development, among others. Traditional methods focus on syntactic pattern-based approaches, typically context-agnostic, evaluated on a closed set of apps, difficult to replicate and limited to a reduced set and domain of apps. Meanwhile, the pervasiveness of Large Language Models (LLMs) based on the Transformer architecture in software engineering tasks lays the groundwork for empirical evaluation of the performance of these models to support feature extraction. In this study, we present T-FREX, a Transformer-based, fully automatic approach for mobile app review feature extraction. First, we collect a set of ground truth features from users in a real crowdsourced software recommendation platform and transfer them automatically into a dataset of app reviews. Then, we use this newly created dataset to fine-tune multiple LLMs on a named entity recognition task under different data configurations. We assess the performance of T-FREX with respect to this ground truth, and we complement our analysis by comparing T-FREX with a baseline method from the field. Finally, we assess the quality of new features predicted by T-FREX through an external human evaluation. Results show that T-FREX outperforms on average the traditional syntactic-based method, especially when discovering new features from a domain for which the model has been fine-tuned.

cs.SE↗

arXiv2023

Exploring the Carbon Footprint of Hugging Face's ML Models: A Repository Mining Study

The rise of machine learning (ML) systems has exacerbated their carbon footprint due to increased capabilities and model sizes. However, there is scarce knowledge on how the carbon footprint of ML models is actually measured, reported, and evaluated. In light of this, the paper aims to analyze the measurement of the carbon footprint of 1,417 ML models and associated datasets on Hugging Face, which is the most popular repository for pretrained ML models. The goal is to provide insights and recommendations on how to report and optimize the carbon efficiency of ML models. The study includes the first repository mining study on the Hugging Face Hub API on carbon emissions. This study seeks to answer two research questions: (1) how do ML model creators measure and report carbon emissions on Hugging Face Hub?, and (2) what aspects impact the carbon emissions of training ML models? The study yielded several key findings. These include a stalled proportion of carbon emissions-reporting models, a slight decrease in reported carbon footprint on Hugging Face over the past 2 years, and a continued dominance of NLP as the main application domain. Furthermore, the study uncovers correlations between carbon emissions and various attributes such as model size, dataset size, and ML application domains. These results highlight the need for software measurements to improve energy reporting practices and promote carbon-efficient model development within the Hugging Face community. In response to this issue, two classifications are proposed: one for categorizing models based on their carbon emission reporting practices and another for their carbon efficiency. The aim of these classification proposals is to foster transparency and sustainable model development within the ML community.

cs.LG↗

arXiv2023

Towards green AI-based software systems: an architecture-centric approach (GAISSA)

Nowadays, AI-based systems have achieved outstanding results and have outperformed humans in different domains. However, the processes of training AI models and inferring from them require high computational resources, which pose a significant challenge in the current energy efficiency societal demand. To cope with this challenge, this research project paper describes the main vision, goals, and expected outcomes of the GAISSA project. The GAISSA project aims at providing data scientists and software engineers tool-supported, architecture-centric methods for the modelling and development of green AI-based systems. Although the project is in an initial stage, we describe the current research results, which illustrate the potential to achieve GAISSA objectives.

cs.SE↗

arXiv2023

Which Design Decisions in AI-enabled Mobile Applications Contribute to Greener AI?

Background: The construction, evolution and usage of complex artificial intelligence (AI) models demand expensive computational resources. While currently available high-performance computing environments support well this complexity, the deployment of AI models in mobile devices, which is an increasing trend, is challenging. Mobile applications consist of environments with low computational resources and hence imply limitations in the design decisions during the AI-enabled software engineering lifecycle that balance the trade-off between the accuracy and the complexity of the mobile applications. Objective: Our objective is to systematically assess the trade-off between accuracy and complexity when deploying complex AI models (e.g. neural networks) to mobile devices, which have an implicit resource limitation. We aim to cover (i) the impact of the design decisions on the achievement of high-accuracy and low resource-consumption implementations; and (ii) the validation of profiling tools for systematically promoting greener AI. Method: This confirmatory registered report consists of a plan to conduct an empirical study to quantify the implications of the design decisions on AI-enabled applications performance and to report experiences of the end-to-end AI-enabled software engineering lifecycle. Concretely, we will implement both image-based and language-based neural networks in mobile applications to solve multiple image classification and text classification problems on different benchmark datasets. Overall, we plan to model the accuracy and complexity of AI-enabled applications in operation with respect to their design decisions and will provide tools for allowing practitioners to gain consciousness of the quantitative relationship between the design decisions and the green characteristics of study.

cs.LG↗

arXiv2023

Energy Efficiency of Training Neural Network Architectures: An Empirical Study

The evaluation of Deep Learning models has traditionally focused on criteria such as accuracy, F1 score, and related measures. The increasing availability of high computational power environments allows the creation of deeper and more complex models. However, the computations needed to train such models entail a large carbon footprint. In this work, we study the relations between DL model architectures and their environmental impact in terms of energy consumed and CO$_2$ emissions produced during training by means of an empirical study using Deep Convolutional Neural Networks. Concretely, we study: (i) the impact of the architecture and the location where the computations are hosted on the energy consumption and emissions produced; (ii) the trade-off between accuracy and energy efficiency; and (iii) the difference on the method of measurement of the energy consumed using software-based and hardware-based tools.

cs.LG↗

arXiv2022

Improved management of issue dependencies in issue trackers of large collaborative projects

Issue trackers, such as Jira, have become the prevalent collaborative tools in software engineering for managing issues, such as requirements, development tasks, and software bugs. However, issue trackers inherently focus on the lifecycle of single issues, although issues have and express dependencies on other issues that constitute issue dependency networks in large complex collaborative projects. The objective of this study is to develop supportive solutions for the improved management of dependent issues in an issue tracker. This study follows the Design Science methodology, consisting of eliciting drawbacks and constructing and evaluating a solution and system. The study was carried out in the context of The Qt Company's Jira, which exemplifies an actively used, almost two-decade-old issue tracker with over 100,000 issues. The drawbacks capture how users operate with issue trackers to handle issue information in large, collaborative, and long-lived projects. The basis of the solution is to keep issues and dependencies as separate objects and automatically construct an issue graph. Dependency detections complement the issue graph by proposing missing dependencies, while consistency checks and diagnoses identify conflicting issue priorities and release assignments. Jira's plugin and service-based system architecture realize the functional and quality concerns of the system implementation. We show how to adopt the intelligent supporting techniques of an issue tracker in a complex use context and a large data-set. The solution considers an integrated and holistic system view, practical applicability and utility, and the practical characteristics of issue data, such as inherent incompleteness.

cs.SE↗