{"title":"The Case for Hybrid Multi-Objective Optimisation in High-Stakes Machine Learning Applications","authors":"Alex A. Freitas","doi":"10.1145/3682112.3682116","DOIUrl":"https://doi.org/10.1145/3682112.3682116","url":null,"abstract":"Most classification (supervised learning) algorithms optimise a single objective, typically the predictive performance of the learned classification model. However, in high-stake classification applications, involving e.g. decisions about whether or not an individual should undergo a medical surgery, be granted a loan or be hired for a job, often there is a need to optimise multiple objectives, such as the predictive performance, interpretability or fairness of the learned model. In this context, this position paper discusses the pros and cons of two different multi-objective optimisation approaches (the Pareto and the lexicographic approaches), and proposes a conceptual framework for hybrid multi-objective optimisation, combining those two approaches.","PeriodicalId":294240,"journal":{"name":"ACM SIGKDD Explorations Newsletter","volume":"41 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tristan Allard, Hira Asghar, Gildas Avoine, Christophe Bobineau, P. Cauchois, Elisa Fromont, Anna Monreale, Francesca Naretto, Roberto Pellungrini, Francesca Pratesi, M. Rousset, Antonin Voyez
{"title":"Analyzing and explaining privacy risks on time series data: ongoing work and challenges","authors":"Tristan Allard, Hira Asghar, Gildas Avoine, Christophe Bobineau, P. Cauchois, Elisa Fromont, Anna Monreale, Francesca Naretto, Roberto Pellungrini, Francesca Pratesi, M. Rousset, Antonin Voyez","doi":"10.1145/3682112.3682118","DOIUrl":"https://doi.org/10.1145/3682112.3682118","url":null,"abstract":"Currently, privacy risks assessment is mainly performed as audits conducted by data privacy analysts. In the TAILOR project, we promote a more systematic and automatic approach based on interpretable metrics and formal methods to evaluate privacy risks and to control the tension between data privacy and utility. In this paper, we focus on privacy risks raised by publishing time series datasets, and we survey the methods developed in TAILOR to analyze and quantify privacy risks depending on different publisher and attacker models.","PeriodicalId":294240,"journal":{"name":"ACM SIGKDD Explorations Newsletter","volume":"55 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141808840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Synthetic data for learning-based knowledge discovery","authors":"William Shiao, E. Papalexakis","doi":"10.1145/3682112.3682115","DOIUrl":"https://doi.org/10.1145/3682112.3682115","url":null,"abstract":"Recent advances in deep learning have demonstrated the ability of learning-based methods to tackle very hard downstream tasks. Historically, this has been demonstrated in predictive tasks, while tasks more akin to the traditional KDD (Knowledge Discovery in Databases) pipeline have enjoyed proportionally fewer advances. Can learning-based approaches help with inherently hard problems within the KDD pipeline, such as \"how many patterns are in the data\", \"what are different structures in the data\", and \"how can we robustly extract those structures?\" In this vision paper, we argue for the need for synthetic data generators to empower cheaply-supervised learning-based solutions for knowledge discovery. We describe the general idea, early proof-of-concept results which speak to the viability of the paradigm, and we outline a number of exciting challenges that await, and a set of milestones for measuring success.","PeriodicalId":294240,"journal":{"name":"ACM SIGKDD Explorations Newsletter","volume":"40 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141809816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Storage Systems: Organization, Performance, Coding, Reliability, and Their Data Processing, 1st Edition, October 13, 2021, Author: Alexander Thomasian","authors":"A. Thomasian","doi":"10.1145/3655103.3655107","DOIUrl":"https://doi.org/10.1145/3655103.3655107","url":null,"abstract":"Textbooks on computer organization and architecture, operating systems, and databases do not sufficiently cover storage systems. This is especially so in view of rapid advances in storage technology in the form of flash and Storage Class Memories - SCMs and storage organizations such as datacentric and the DisAggregated Shared Everything - DASE.","PeriodicalId":294240,"journal":{"name":"ACM SIGKDD Explorations Newsletter","volume":"103 46","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140379659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mirko Bunse, Pablo Gonz´alez, Alejandro Moreo, Fabrizio Sebastiani
{"title":"Report on the 3rd International Workshop onLearning to Quantify (LQ 2023)","authors":"Mirko Bunse, Pablo Gonz´alez, Alejandro Moreo, Fabrizio Sebastiani","doi":"10.1145/3655103.3655108","DOIUrl":"https://doi.org/10.1145/3655103.3655108","url":null,"abstract":"The 3rd International Workshop on Learning to Quantify (LQ 2023)1 took place on September 18, 2023 in Torino, IT, where it was organised as a satellite event of the 34th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2023). Like the main program of the conference, the workshop employed a hybrid format, with all presentations given in presence and with attendees participating in presence or online. This report presents a summary of the workshop, briefly summarising the individual works presented, and touching on the main issues that emerged during the final, open discussion.","PeriodicalId":294240,"journal":{"name":"ACM SIGKDD Explorations Newsletter","volume":"123 41","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140381002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Anomaly Detection using Generative Adversarial Networks\u0000 Reviewing methodological progress and challenges","authors":"Fiete Lüer, Christian Bohm","doi":"10.1145/3655103.3655109","DOIUrl":"https://doi.org/10.1145/3655103.3655109","url":null,"abstract":"The applications of Generative Adversarial Networks (GANs) are just as diverse as their architectures, problem settings as well as challenges. A key area of research on GANs is anomaly detection where they are most often utilized when only the data of one class is readily available.\u0000 In this work, we organize, summarize and compare key concepts and challenges of anomaly detection based on GANs. Common problems which have to be investigated to progress the applicability of GANs are identified and discussed. This includes stability and time requirements during training as well as inference, the restriction of the latent space to produce solely data from the normal class distribution, contaminated training data as well as the composition of the resulting anomaly detection score. We discuss the problems using existing work as well as possible (partial) solutions, including related work from similar areas of research such as related generative models or novelty detection. Our findings are also relevant for a variety of closely related generative modeling approaches, such as autoencoders, and are of interest for areas of research tangent to anomaly detection such as image inpainting or image translation.","PeriodicalId":294240,"journal":{"name":"ACM SIGKDD Explorations Newsletter","volume":"120 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140378904","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}