Artificial intelligence, machine learning, and algorithmic techniques in general, provide two crucial abilities with the potential to improve decision-making in the context of allocation of scarce societal resources. They have the ability to flexibly and accurately model treatment response at the individual level, potentially allowing us to better match available resources to individuals. In addition, they have the ability to reason simultaneously about the effects of matching sets of scarce resources to populations of individuals. In this work, we leverage these abilities to study algorithmic allocation of scarce societal resources in the context of homelessness. In communities throughout the United States, there is constant demand for an array of homeless services intended to address different levels of need. Allocations of housing services must match households to appropriate services that continuously fluctuate in availability, while inefficiencies in allocation could “waste” scarce resources as households will remain in-need and re-enter the homeless system, increasing the overall demand for homeless services. This complex allocation problem introduces novel technical and ethical challenges. Using administrative data from a regional homeless system, we formulate the problem of “optimal” allocation of resources given data on households with need for homeless services. The optimization problem aims to allocate available resources such that predicted probabilities of household re-entry are minimized. The key element of this work is its use of a counterfactual prediction approach that predicts household probabilities of re-entry into homeless services if assigned to each service. Through these counterfactual predictions, we find that this approach has the potential to improve the efficiency of the homeless system by reducing re-entry, and, therefore, system-wide demand. However, efficiency comes with trade-offs - a significant fraction of households are assigned to services that increase probability of re-entry. To address this issue as well as the inherent fairness considerations present in any context where there are insufficient resources to meet demand, we discuss the efficiency, equity, and fairness issues that arise in our work and consider potential implications for homeless policies.
{"title":"Fair and Efficient Allocation of Scarce Resources Based on Predicted Outcomes: Implications for Homeless Service Delivery","authors":"Amanda Kube, Sanmay Das, P. Fowler","doi":"10.1613/jair.1.12847","DOIUrl":"https://doi.org/10.1613/jair.1.12847","url":null,"abstract":"Artificial intelligence, machine learning, and algorithmic techniques in general, provide two crucial abilities with the potential to improve decision-making in the context of allocation of scarce societal resources. They have the ability to flexibly and accurately model treatment response at the individual level, potentially allowing us to better match available resources to individuals. In addition, they have the ability to reason simultaneously about the effects of matching sets of scarce resources to populations of individuals. In this work, we leverage these abilities to study algorithmic allocation of scarce societal resources in the context of homelessness. In communities throughout the United States, there is constant demand for an array of homeless services intended to address different levels of need. Allocations of housing services must match households to appropriate services that continuously fluctuate in availability, while inefficiencies in allocation could “waste” scarce resources as households will remain in-need and re-enter the homeless system, increasing the overall demand for homeless services. This complex allocation problem introduces novel technical and ethical challenges. Using administrative data from a regional homeless system, we formulate the problem of “optimal” allocation of resources given data on households with need for homeless services. The optimization problem aims to allocate available resources such that predicted probabilities of household re-entry are minimized. The key element of this work is its use of a counterfactual prediction approach that predicts household probabilities of re-entry into homeless services if assigned to each service. Through these counterfactual predictions, we find that this approach has the potential to improve the efficiency of the homeless system by reducing re-entry, and, therefore, system-wide demand. However, efficiency comes with trade-offs - a significant fraction of households are assigned to services that increase probability of re-entry. To address this issue as well as the inherent fairness considerations present in any context where there are insufficient resources to meet demand, we discuss the efficiency, equity, and fairness issues that arise in our work and consider potential implications for homeless policies.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"188 1","pages":"1219-1245"},"PeriodicalIF":5.0,"publicationDate":"2023-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76057668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapidly growing of location-based social networks, point-of-interest (POI) recommendation has been attracting tremendous attentions. Previous works for POI recommendation usually use matrix factorization (MF)-based methods, which achieve promising performance. However, existing MF-based methods suffer from two critical limitations: (1) Privacy issues: all users’ sensitive data are collected to the centralized server which may leak on either the server side or during transmission. (2) Poor resource utilization and training efficiency: training on centralized server with potentially huge low-rank matrices is computational inefficient. In this paper, we propose a novel decentralized gradient-quantization based matrix factorization (DGMF) framework to address the above limitations in POI recommendation. Compared with the centralized MF methods which store all sensitive data and low-rank matrices during model training, DGMF treats each user’s device (e.g., phone) as an independent learner and keeps the sensitive data on each user’s end. Furthermore, a privacy-preserving and communication-efficient mechanism with gradient-quantization technique is presented to train the proposed model, which aims to handle the privacy problem and reduces the communication cost in the decentralized setting. Theoretical guarantees of the proposed algorithm and experimental studies on real-world datasets demonstrate the effectiveness of the proposed algorithm.
{"title":"Decentralized Gradient-Quantization Based Matrix Factorization for Fast Privacy-Preserving Point-of-Interest Recommendation","authors":"Xuebin Zhou, Zhibin Hu, Jin Huang, Jing Chen","doi":"10.1613/jair.1.14414","DOIUrl":"https://doi.org/10.1613/jair.1.14414","url":null,"abstract":"With the rapidly growing of location-based social networks, point-of-interest (POI) recommendation has been attracting tremendous attentions. Previous works for POI recommendation usually use matrix factorization (MF)-based methods, which achieve promising performance. However, existing MF-based methods suffer from two critical limitations: (1) Privacy issues: all users’ sensitive data are collected to the centralized server which may leak on either the server side or during transmission. (2) Poor resource utilization and training efficiency: training on centralized server with potentially huge low-rank matrices is computational inefficient. In this paper, we propose a novel decentralized gradient-quantization based matrix factorization (DGMF) framework to address the above limitations in POI recommendation. Compared with the centralized MF methods which store all sensitive data and low-rank matrices during model training, DGMF treats each user’s device (e.g., phone) as an independent learner and keeps the sensitive data on each user’s end. Furthermore, a privacy-preserving and communication-efficient mechanism with gradient-quantization technique is presented to train the proposed model, which aims to handle the privacy problem and reduces the communication cost in the decentralized setting. Theoretical guarantees of the proposed algorithm and experimental studies on real-world datasets demonstrate the effectiveness of the proposed algorithm.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"101 1","pages":"1019-1041"},"PeriodicalIF":5.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80333745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper analyzes cooperative data-sharing between competitors vying to predict a consumer's tastes. We design optimal data-sharing schemes both for when they compete only with each other, and for when they additionally compete with an Amazon – a company with more, better data. We show that simple schemes – threshold rules that probabilistically induce either full data-sharing between competitors, or the full transfer of data from one competitor to another – are either optimal or approximately optimal, depending on properties of the information structure. We also provide conditions under which firms share more data when they face stronger outside competition, and describe situations in which this conclusion is reversed.
{"title":"Coopetition Against an Amazon","authors":"Ronen Gradwohl, Moshe Tennenholtz","doi":"10.1613/jair.1.14074","DOIUrl":"https://doi.org/10.1613/jair.1.14074","url":null,"abstract":"This paper analyzes cooperative data-sharing between competitors vying to predict a consumer's tastes. We design optimal data-sharing schemes both for when they compete only with each other, and for when they additionally compete with an Amazon – a company with more, better data. We show that simple schemes – threshold rules that probabilistically induce either full data-sharing between competitors, or the full transfer of data from one competitor to another – are either optimal or approximately optimal, depending on properties of the information structure. We also provide conditions under which firms share more data when they face stronger outside competition, and describe situations in which this conclusion is reversed.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136020959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We consider an outsourcing problem where a software agent procures multiple services from providers with uncertain reliabilities to complete a computational task before a strict deadline. The service consumer’s goal is to design an outsourcing strategy (defining which services to procure and when) so as to maximize a specific objective function. This objective function can be different based on the consumer’s nature; a socially-focused consumer often aims to maximize social welfare, while a self-interested consumer often aims to maximize its own utility. However, in both cases, the objective function depends on the providers’ execution costs, which are privately held by the self-interested providers and hence may be misreported to influence the consumer’s decisions. For such settings, we develop a unified approach to design truthful procurement auctions that can be used by both socially-focused and, separately, self-interested consumers. This approach benefits from our proposed weighted threshold payment scheme which pays the provably minimum amount to make an auction with a monotone outsourcing strategy incentive compatible. This payment scheme can handle contingent outsourcing plans, where additional procurement happens gradually over time and only if the success probability of the already hired providers drops below a time-dependent threshold. Using a weighted threshold payment scheme, we design two procurement auctions that maximize, as well as two low-complexity heuristic-based auctions that approximately maximize, the consumer’s expected utility and expected social welfare, respectively. We demonstrate the effectiveness and strength of our proposed auctions through both game-theoretical and empirical analysis.
{"title":"Optimal and Efficient Auctions for the Gradual Procurement of Strategic Service Provider Agents","authors":"F. Farhadi, Maria Chli, N. Jennings","doi":"10.1613/jair.1.14126","DOIUrl":"https://doi.org/10.1613/jair.1.14126","url":null,"abstract":"We consider an outsourcing problem where a software agent procures multiple services from providers with uncertain reliabilities to complete a computational task before a strict deadline. The service consumer’s goal is to design an outsourcing strategy (defining which services to procure and when) so as to maximize a specific objective function. This objective function can be different based on the consumer’s nature; a socially-focused consumer often aims to maximize social welfare, while a self-interested consumer often aims to maximize its own utility. However, in both cases, the objective function depends on the providers’ execution costs, which are privately held by the self-interested providers and hence may be misreported to influence the consumer’s decisions. For such settings, we develop a unified approach to design truthful procurement auctions that can be used by both socially-focused and, separately, self-interested consumers. This approach benefits from our proposed weighted threshold payment scheme which pays the provably minimum amount to make an auction with a monotone outsourcing strategy incentive compatible. This payment scheme can handle contingent outsourcing plans, where additional procurement happens gradually over time and only if the success probability of the already hired providers drops below a time-dependent threshold. Using a weighted threshold payment scheme, we design two procurement auctions that maximize, as well as two low-complexity heuristic-based auctions that approximately maximize, the consumer’s expected utility and expected social welfare, respectively. We demonstrate the effectiveness and strength of our proposed auctions through both game-theoretical and empirical analysis. ","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"111 1","pages":"959-1018"},"PeriodicalIF":5.0,"publicationDate":"2023-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77877737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Influence maximization is the problem of finding a set of seed nodes in the network that maximizes the influence spread, which has become an important topic in social network analysis. Conventional influence maximization algorithms cause “unfair" influence spread among different groups in the population, which could lead to severe bias in public opinion dissemination and viral marketing. To address this issue, we formulate the fair influence maximization problem concerning the trade-off between influence maximization and group fairness. For the purpose of solving the fair influence maximization problem in large-scale social networks efficiently, we propose a novel attribute-based reverse influence sampling (ABRIS) framework. This framework intends to estimate influence in specific groups with guarantee through an attribute-based hypergraph so that we can select seed nodes strategically. Therefore, under the ABRIS framework, we design two different node selection algorithms, ABRIS-G and ABRIS-T. ABRIS-G selects nodes in a greedy scheduling way. ABRIS-T adopts a two-phase node selection method. These algorithms run efficiently and achieve a good trade-off between influence maximization and group fairness. Extensive experiments on six real-world social networks show that our algorithms significantly outperform the state-of-the-art approaches. This article appears in the AI & Society track.
{"title":"Fair Influence Maximization in Large-scale Social Networks Based on Attribute-aware Reverse Influence Sampling","authors":"Mingkai Lin, Lintan Sun, Rui Yang, Xu-Sheng Liu, Yajuan Wang, Ding Li, Wenzhong Li, Sanglu Lu","doi":"10.1613/jair.1.14450","DOIUrl":"https://doi.org/10.1613/jair.1.14450","url":null,"abstract":"Influence maximization is the problem of finding a set of seed nodes in the network that maximizes the influence spread, which has become an important topic in social network analysis. Conventional influence maximization algorithms cause “unfair\" influence spread among different groups in the population, which could lead to severe bias in public opinion dissemination and viral marketing. To address this issue, we formulate the fair influence maximization problem concerning the trade-off between influence maximization and group fairness. For the purpose of solving the fair influence maximization problem in large-scale social networks efficiently, we propose a novel attribute-based reverse influence sampling (ABRIS) framework. This framework intends to estimate influence in specific groups with guarantee through an attribute-based hypergraph so that we can select seed nodes strategically. Therefore, under the ABRIS framework, we design two different node selection algorithms, ABRIS-G and ABRIS-T. ABRIS-G selects nodes in a greedy scheduling way. ABRIS-T adopts a two-phase node selection method. These algorithms run efficiently and achieve a good trade-off between influence maximization and group fairness. Extensive experiments on six real-world social networks show that our algorithms significantly outperform the state-of-the-art approaches.\u0000This article appears in the AI & Society track.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"18 1","pages":"925-957"},"PeriodicalIF":5.0,"publicationDate":"2023-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91302847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ricardo Guimarães, A. Ozaki, Cosimo Persia, B. Sertkaya
In Formal Concept Analysis, a base for a finite structure is a set of implications that characterizes all valid implications of the structure. This notion can be adapted to the context of Description Logic, where the base consists of a set of concept inclusions instead of implications. In this setting, concept expressions can be arbitrarily large. Thus, it is not clear whether a finite base exists and, if so, how large concept expressions may need to be. We first revisit results in the literature for mining ℰℒ⊥ bases from finite interpretations. Those mainly focus on finding a finite base or on fixing the role depth but potentially losing some of the valid concept inclusions with higher role depth. We then present a new strategy for mining ℰℒ⊥ bases which is adaptable in the sense that it can bound the role depth of concepts depending on the local structure of the interpretation. Our strategy guarantees to capture all ℰℒ⊥ concept inclusions holding in the interpretation, not only the ones up to a fixed role depth. We also consider the case of confident ℰℒ⊥ bases, which requires that some proportion of the domain of the interpretation satisfies the base, instead of the whole domain. This case is useful to cope with noisy data.
{"title":"Mining ℰℒ⊥ Bases with Adaptable Role Depth","authors":"Ricardo Guimarães, A. Ozaki, Cosimo Persia, B. Sertkaya","doi":"10.1613/jair.1.13777","DOIUrl":"https://doi.org/10.1613/jair.1.13777","url":null,"abstract":"In Formal Concept Analysis, a base for a finite structure is a set of implications that characterizes all valid implications of the structure. This notion can be adapted to the context of Description Logic, where the base consists of a set of concept inclusions instead of implications. In this setting, concept expressions can be arbitrarily large. Thus, it is not clear whether a finite base exists and, if so, how large concept expressions may need to be. We first revisit results in the literature for mining ℰℒ⊥ bases from finite interpretations. Those mainly focus on finding a finite base or on fixing the role depth but potentially losing some of the valid concept inclusions with higher role depth. We then present a new strategy for mining ℰℒ⊥ bases which is adaptable in the sense that it can bound the role depth of concepts depending on the local structure of the interpretation. Our strategy guarantees to capture all ℰℒ⊥ concept inclusions holding in the interpretation, not only the ones up to a fixed role depth. We also consider the case of confident ℰℒ⊥ bases, which requires that some proportion of the domain of the interpretation satisfies the base, instead of the whole domain. This case is useful to cope with noisy data.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"2 1","pages":"883-924"},"PeriodicalIF":5.0,"publicationDate":"2023-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90255511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The recent rise of machine learning (ML) has been leveraged by practitioners and researchers to provide new solutions to an ever growing number of business problems. As with other ML applications, these solutions rely on model selection, which is typically achieved by evaluating certain metrics on models separately and selecting the model whose evaluations (i.e., accuracy-related loss and/or certain interpretability measures) are optimal. However, empirical evidence suggests that, in practice, multiple models often attain competitive results. Therefore, while models’ overall performance could be similar, they could operate quite differently. This results in an implicit tradeoff in models’ performance throughout the feature space which resolving requires new model selection tools. This paper explores methods for comparing predictive models in an interpretable manner to uncover the tradeoff and help resolve it. To this end, we propose various methods that synthesize ideas from supervised learning, unsupervised learning, dimensionality reduction, and visualization to demonstrate how they can be used to inform model developers about the model selection process. Using various datasets and a simple Python interface, we demonstrate how practitioners and researchers could benefit from applying these approaches to better understand the broader impact of their model selection choices.
{"title":"Visualizing the Implicit Model Selection Tradeoff","authors":"Zezhen He, Yaron Shaposhnik","doi":"10.1613/jair.1.13764","DOIUrl":"https://doi.org/10.1613/jair.1.13764","url":null,"abstract":"The recent rise of machine learning (ML) has been leveraged by practitioners and researchers to provide new solutions to an ever growing number of business problems. As with other ML applications, these solutions rely on model selection, which is typically achieved by evaluating certain metrics on models separately and selecting the model whose evaluations (i.e., accuracy-related loss and/or certain interpretability measures) are optimal. However, empirical evidence suggests that, in practice, multiple models often attain competitive results. Therefore, while models’ overall performance could be similar, they could operate quite differently. This results in an implicit tradeoff in models’ performance throughout the feature space which resolving requires new model selection tools. This paper explores methods for comparing predictive models in an interpretable manner to uncover the tradeoff and help resolve it. To this end, we propose various methods that synthesize ideas from supervised learning, unsupervised learning, dimensionality reduction, and visualization to demonstrate how they can be used to inform model developers about the model selection process. Using various datasets and a simple Python interface, we demonstrate how practitioners and researchers could benefit from applying these approaches to better understand the broader impact of their model selection choices.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"291 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135733029","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We study fair allocation of indivisible goods among additive agents with feasibility constraints. In these settings, every agent is restricted to get a bundle among a specified set of feasible bundles. Such scenarios have been of great interest to the AI community due to their applicability to real-world problems. Following some impossibility results, we restrict attention to matroid feasibility constraints that capture natural scenarios, such as the allocation of shifts to medical doctors and the allocation of conference papers to referees. We focus on the common fairness notion of envy-freeness up to one good (EF1). Previous algorithms for finding EF1 allocations are either restricted to agents with identical feasibility constraints or allow free disposal of items. An open problem is the existence of EF1 complete allocations among agents who differ both in their valuations and in their feasibility constraints. In this work, we make progress on this problem by providing positive and negative results for several matroid and valuation types. Among other results, we devise polynomial-time algorithms for finding EF1 allocations in the following settings: (i) n agents with heterogeneous (non-identical) binary valuations and partition matroids with heterogeneous capacities; (ii) two agents with heterogeneous additive valuations and partition matroids with heterogeneous capacities; and (iii) three agents with heterogeneous binary valuations and identical base-orderable matroid constraints.
{"title":"On Fair Division under Heterogeneous Matroid Constraints","authors":"Amitay Dror, Michal Feldman, Erel Segal-Halevi","doi":"10.1613/jair.1.13779","DOIUrl":"https://doi.org/10.1613/jair.1.13779","url":null,"abstract":"We study fair allocation of indivisible goods among additive agents with feasibility constraints. In these settings, every agent is restricted to get a bundle among a specified set of feasible bundles. Such scenarios have been of great interest to the AI community due to their applicability to real-world problems. Following some impossibility results, we restrict attention to matroid feasibility constraints that capture natural scenarios, such as the allocation of shifts to medical doctors and the allocation of conference papers to referees. We focus on the common fairness notion of envy-freeness up to one good (EF1). Previous algorithms for finding EF1 allocations are either restricted to agents with identical feasibility constraints or allow free disposal of items. An open problem is the existence of EF1 complete allocations among agents who differ both in their valuations and in their feasibility constraints. In this work, we make progress on this problem by providing positive and negative results for several matroid and valuation types. Among other results, we devise polynomial-time algorithms for finding EF1 allocations in the following settings: (i) n agents with heterogeneous (non-identical) binary valuations and partition matroids with heterogeneous capacities; (ii) two agents with heterogeneous additive valuations and partition matroids with heterogeneous capacities; and (iii) three agents with heterogeneous binary valuations and identical base-orderable matroid constraints.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136007438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
N. Ponomareva, Hussein Hazimeh, Alexey Kurakin, Zheng Xu, Carson E. Denison, H. B. McMahan, Sergei Vassilvitskii, Steve Chien, Abhradeep Thakurta
Machine Learning (ML) models are ubiquitous in real-world applications and are a constant focus of research. Modern ML models have become more complex, deeper, and harder to reason about. At the same time, the community has started to realize the importance of protecting the privacy of the training data that goes into these models. Differential Privacy (DP) has become a gold standard for making formal statements about data anonymization. However, while some adoption of DP has happened in industry, attempts to apply DP to real world complex ML models are still few and far between. The adoption of DP is hindered by limited practical guidance of what DP protection entails, what privacy guarantees to aim for, and the difficulty of achieving good privacy-utility-computation trade-offs for ML models. Tricks for tuning and maximizing performance are scattered among papers or stored in the heads of practitioners, particularly with respect to the challenging task of hyperparameter tuning. Furthermore, the literature seems to present conflicting evidence on how and whether to apply architectural adjustments and which components are “safe” to use with DP. In this survey paper, we attempt to create a self-contained guide that gives an in-depth overview of the field of DP ML. We aim to assemble information about achieving the best possible DP ML model with rigorous privacy guarantees. Our target audience is both researchers and practitioners. Researchers interested in DP for ML will benefit from a clear overview of current advances and areas for improvement. We also include theory-focused sections that highlight important topics such as privacy accounting and convergence. For a practitioner, this survey provides a background in DP theory and a clear step-by-step guide for choosing an appropriate privacy definition and approach, implementing DP training, potentially updating the model architecture, and tuning hyperparameters. For both researchers and practitioners, consistently and fully reporting privacy guarantees is critical, so we propose a set of specific best practices for stating guarantees. With sufficient computation and a sufficiently large training set or supplemental nonprivate data, both good accuracy (that is, almost as good as a non-private model) and good privacy can often be achievable. And even when computation and dataset size are limited, there are advantages to training with even a weak (but still finite) formal DP guarantee. Hence, we hope this work will facilitate more widespread deployments of DP ML models.
{"title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","authors":"N. Ponomareva, Hussein Hazimeh, Alexey Kurakin, Zheng Xu, Carson E. Denison, H. B. McMahan, Sergei Vassilvitskii, Steve Chien, Abhradeep Thakurta","doi":"10.1613/jair.1.14649","DOIUrl":"https://doi.org/10.1613/jair.1.14649","url":null,"abstract":"Machine Learning (ML) models are ubiquitous in real-world applications and are a constant focus of research. Modern ML models have become more complex, deeper, and harder to reason about. At the same time, the community has started to realize the importance of protecting the privacy of the training data that goes into these models.\u0000Differential Privacy (DP) has become a gold standard for making formal statements about data anonymization. However, while some adoption of DP has happened in industry, attempts to apply DP to real world complex ML models are still few and far between. The adoption of DP is hindered by limited practical guidance of what DP protection entails, what privacy guarantees to aim for, and the difficulty of achieving good privacy-utility-computation trade-offs for ML models. Tricks for tuning and maximizing performance are scattered among papers or stored in the heads of practitioners, particularly with respect to the challenging task of hyperparameter tuning. Furthermore, the literature seems to present conflicting evidence on how and whether to apply architectural adjustments and which components are “safe” to use with DP.\u0000In this survey paper, we attempt to create a self-contained guide that gives an in-depth overview of the field of DP ML. We aim to assemble information about achieving the best possible DP ML model with rigorous privacy guarantees. Our target audience is both researchers and practitioners. Researchers interested in DP for ML will benefit from a clear overview of current advances and areas for improvement. We also include theory-focused sections that highlight important topics such as privacy accounting and convergence. For a practitioner, this survey provides a background in DP theory and a clear step-by-step guide for choosing an appropriate privacy definition and approach, implementing DP training, potentially updating the model architecture, and tuning hyperparameters. For both researchers and practitioners, consistently and fully reporting privacy guarantees is critical, so we propose a set of specific best practices for stating guarantees.\u0000With sufficient computation and a sufficiently large training set or supplemental nonprivate data, both good accuracy (that is, almost as good as a non-private model) and good privacy can often be achievable. And even when computation and dataset size are limited, there are advantages to training with even a weak (but still finite) formal DP guarantee. Hence, we hope this work will facilitate more widespread deployments of DP ML models.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"384 1","pages":"1113-1201"},"PeriodicalIF":5.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77762609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Du, N. Alechina, Amin Farjudian, B. Logan, Can Zhou, A. Cohn
We propose a logic of east and west (LEW ) for points in 1D Euclidean space. It formalises primitive direction relations: east (E), west (W) and indeterminate east/west (Iew). It has a parameter τ ∈ N>1, which is referred to as the level of indeterminacy in directions. For every τ ∈ N>1, we provide a sound and complete axiomatisation of LEW , and prove that its satisfiability problem is NP-complete. In addition, we show that the finite axiomatisability of LEW depends on τ : if τ = 2 or τ = 3, then there exists a finite sound and complete axiomatisation; if τ > 3, then the logic is not finitely axiomatisable. LEW can be easily extended to higher-dimensional Euclidean spaces. Extending LEW to 2D Euclidean space makes it suitable for reasoning about not perfectly aligned representations of the same spatial objects in different datasets, for example, in crowd-sourced digital maps.
{"title":"A Logic of East and West","authors":"H. Du, N. Alechina, Amin Farjudian, B. Logan, Can Zhou, A. Cohn","doi":"10.1613/jair.1.14113","DOIUrl":"https://doi.org/10.1613/jair.1.14113","url":null,"abstract":"We propose a logic of east and west (LEW ) for points in 1D Euclidean space. It formalises primitive direction relations: east (E), west (W) and indeterminate east/west (Iew). It has a parameter τ ∈ N>1, which is referred to as the level of indeterminacy in directions. For every τ ∈ N>1, we provide a sound and complete axiomatisation of LEW , and prove that its satisfiability problem is NP-complete. In addition, we show that the finite axiomatisability of LEW depends on τ : if τ = 2 or τ = 3, then there exists a finite sound and complete axiomatisation; if τ > 3, then the logic is not finitely axiomatisable. LEW can be easily extended to higher-dimensional Euclidean spaces. Extending LEW to 2D Euclidean space makes it suitable for reasoning about not perfectly aligned representations of the same spatial objects in different datasets, for example, in crowd-sourced digital maps.","PeriodicalId":54877,"journal":{"name":"Journal of Artificial Intelligence Research","volume":"10 1","pages":"527-565"},"PeriodicalIF":5.0,"publicationDate":"2023-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83358357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：