Active learning is a subfield of machine learning, in which the learning algorithm is allowed to choose the data from which it learns. In some cases, it has been shown that active learning can yield an exponential gain in the number of samples the algorithm needs to see, in order to reach generalization error $\leq ε$. In this work we study the problem of learning halfspaces with membership queries. In the membership query scenario, we allow the learning algorithm to ask for the label of every sample in the input space. We suggest a new algorithm for this problem, and prove it achieves a near optimal label complexity in some cases. We also show that the algorithm works well in practice, and significantly outperforms uncertainty sampling.
Technion（以色列理工学院）；Convent of Nazareth School（拿撒勒修道院学校）
We consider the problem of proper learning a Boolean Halfspace with integer weights $\{0,1,\ldots,t\}$ from membership queries only. The best known algorithm for this problem is an adaptive algorithm that asks $n^{O(t^5)}$ membership queries where the best lower bound for the number of membership queries is $n^t$ [Learning Threshold Functions with Small Weights Using Membership Queries. COLT 1999] In this paper we close this gap and give an adaptive proper learning algorithm with two rounds that asks $n^{O(t)}$ membership queries. We also give a non-adaptive proper learning algorithm that asks…
Institute for Data, Econometrics, Algorithms, and Learning (IDEAL)（数据、计量经济学、算法和学习研究所）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；Weizmann Institute of Science（魏茨曼科学研究院）
Carnegie Mellon University（卡内基梅隆大学）；California Institute of Technology（加州理工学院）；University of Pennsylvania（宾夕法尼亚大学）
In this paper we demonstrate that, ignoring computational constraints, it is possible to privately release synthetic databases that are useful for large classes of queries -- much larger in size than the database itself. Specifically, we give a mechanism that privately releases synthetic data for a class of queries over a discrete domain with error that grows as a function of the size of the smallest net approximately representing the answers to that class of queries. We show that this in particular implies a mechanism for counting queries that gives error guarantees that grow only with the VC…
MPI-SWS（马克斯·普朗克软件系统研究所）；Caltech（加州理工学院）；University of Chicago（芝加哥大学）
We examine the task of locating a target region among those induced by intersections of $n$ halfspaces in $\mathbb{R}^d$. This generic task connects to fundamental machine learning problems, such as training a perceptron and learning a $ϕ$-separable dichotomy. We investigate the average teaching complexity of the task, i.e., the minimal number of samples (halfspace queries) required by a teacher to help a version-space learner in locating a randomly selected target. As our main result, we show that the average-case teaching complexity is $Θ(d)$, which is in sharp contrast to the worst-case tea…
Univ. of the Basque Country（巴斯克大学）；Univ. of Brasília（巴西利亚大学）
A major problem in computational learning theory is whether the class of formulas in conjunctive normal form (CNF) is efficiently learnable. Although it is known that this class cannot be polynomially learned using either membership or equivalence queries alone, it is open whether CNF can be polynomially learned using both types of queries. One of the most important results concerning a restriction of the class CNF is that propositional Horn formulas are polynomial time learnable in Angluin's exact learning model with membership and equivalence queries. In this work we push this boundary and s…
We study the problem of efficient PAC active learning of homogeneous linear classifiers (halfspaces) in $\mathbb{R}^d$, where the goal is to learn a halfspace with low error using as few label queries as possible. Under the extra assumption that there is a $t$-sparse halfspace that performs well on the data ($t \ll d$), we would like our active learning algorithm to be {\em attribute efficient}, i.e. to have label requirements sublinear in $d$. In this paper, we provide a computationally efficient algorithm that achieves this goal. Under certain distributional assumptions on the data, our algo…
We consider the well-studied problem of learning intersections of halfspaces under the Gaussian distribution in the challenging \emph{agnostic learning} model. Recent work of Diakonikolas et al. (2021) shows that any Statistical Query (SQ) algorithm for agnostically learning the class of intersections of $k$ halfspaces over $\mathbb{R}^n$ to constant excess error either must make queries of tolerance at most $n^{-\tildeΩ(\sqrt{\log k})}$ or must make $2^{n^{Ω(1)}}$ queries. We strengthen this result by improving the tolerance requirement to $n^{-\tildeΩ(\log k)}$. This lower bound is essential…
In this paper we study the adaptive learnability of decision trees of depth at most $d$ from membership queries. This has many applications in automated scientific discovery such as drugs development and software update problem. Feldman solves the problem in a randomized polynomial time algorithm that asks $\tilde O(2^{2d})\log n$ queries and Kushilevitz-Mansour in a deterministic polynomial time algorithm that asks $ 2^{18d+o(d)}\log n$ queries. We improve the query complexity of both algorithms. We give a randomized polynomial time algorithm that asks $\tilde O(2^{2d}) + 2^{d}\log n$ queries…
TU Kaiserslautern（凯泽斯劳滕工业大学）；Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）
We study the problem of learning a finite union of integer (axis-aligned) hypercubes over the d-dimensional integer lattice, i.e., whose edges are parallel to the coordinate axes. This is a natural generalization of the classic problem in the computational learning theory of learning rectangles. We provide a learning algorithm with access to a minimally adequate teacher (i.e. membership and equivalence oracles) that solves this problem in polynomial-time, for any fixed dimension d. Over a non-fixed dimension, the problem subsumes the problem of learning DNF boolean formulas, a central open pro…
Given a finite set $X \subset \mathbb{R}^d$ and a binary linear classifier $c: \mathbb{R}^d \to \{0,1\}$, how many queries of the form $c(x)$ are required to learn the label of every point in $X$? Known as \textit{point location}, this problem has inspired over 35 years of research in the pursuit of an optimal algorithm. Building on the prior work of Kane, Lovett, and Moran (ICALP 2018), we provide the first nearly optimal solution, a randomized linear decision tree of depth $\tilde{O}(d\log(|X|))$, improving on the previous best of $\tilde{O}(d^2\log(|X|))$ from Ezra and Sharir (Discrete and …
We give tight statistical query (SQ) lower bounds for learnining halfspaces in the presence of Massart noise. In particular, suppose that all labels are corrupted with probability at most $η$. We show that for arbitrary $η\in [0,1/2]$ every SQ algorithm achieving misclassification error better than $η$ requires queries of superpolynomial accuracy or at least a superpolynomial number of queries. Further, this continues to hold even if the information-theoretically optimal error $\mathrm{OPT}$ is as small as $\exp\left(-\log^c(d)\right)$, where $d$ is the dimension and $0 < c < 1$ is an arbitrar…
In this paper, we study adaptive and non-adaptive exact learning of Juntas from membership queries. We use new techniques to find new bounds, narrow some of the gaps between the lower bounds and upper bounds and find new deterministic and randomized algorithms with small query and time complexities. Some of the bounds are tight in the sense that finding better ones either gives a breakthrough result in some long-standing combinatorial open problem or needs a new technique that is beyond the existing ones.
Technion - Israel Institute of Technology（以色列理工学院）
Human labeling of data can be very time-consuming and expensive, yet, in many cases it is critical for the success of the learning process. In order to minimize human labeling efforts, we propose a novel active learning solution that does not rely on existing sources of unlabeled data. It uses a small amount of labeled data as the core set for the synthesis of useful membership queries (MQs) - unlabeled instances generated by an algorithm for human labeling. Our solution uses modification operators, functions that modify instances to some extent. We apply the operators on a small set of instan…
Given a teacher that holds a function $f:X\to R$ from some class of functions $C$. The teacher can receive from the learner an element~$d$ in the domain $X$ (a query) and returns the value of the function in $d$, $f(d)\in R$. The learner goal is to find $f$ with a minimum number of queries, optimal time complexity, and optimal resources. In this survey, we present some of the results known from the literature, different techniques used, some new problems, and open problems.
In this paper, we study the problem of learning a monotone DNF with at most $s$ terms of size (number of variables in each term) at most $r$ ($s$ term $r$-MDNF) from membership queries. This problem is equivalent to the problem of learning a general hypergraph using hyperedge-detecting queries, a problem motivated by applications arising in chemical reactions and genome sequencing. We first present new lower bounds for this problem and then present deterministic and randomized adaptive algorithms with query complexities that are almost optimal. All the algorithms we present in this paper run i…
We define and study the problem of modular concept learning, that is, learning a concept that is a cross product of component concepts. If an element's membership in a concept depends solely on it's membership in the components, learning the concept as a whole can be reduced to learning the components. We analyze this problem with respect to different types of oracle interfaces, defining different sets of queries. If a given oracle interface cannot answer questions about the components, learning can be difficult, even when the components are easy to learn with the same type of oracle queries. …
Let $F$ be a set of boolean functions. We present an algorithm for learning $F_\vee := \{\vee_{f\in S} f \mid S \subseteq F\}$ from membership queries. Our algorithm asks at most $|F| \cdot OPT(F_\vee)$ membership queries where $OPT(F_\vee)$ is the minimum worst case number of membership queries for learning $F_\vee$. When $F$ is a set of halfspaces over a constant dimension space or a set of variable inequalities, our algorithm runs in polynomial time. The problem we address has practical importance in the field of program synthesis, where the goal is to synthesize a program that meets some r…
The Hebrew University（希伯来大学）；Google Research（谷歌研究院）
We consider the natural problem of learning a ReLU network from queries, which was recently remotivated by model extraction attacks. In this work, we present a polynomial-time algorithm that can learn a depth-two ReLU network from queries under mild general position assumptions. We also present a polynomial-time algorithm that, under mild general position assumptions, can learn a rich class of depth-three ReLU networks from queries. For instance, it can learn most networks where the number of first layer neurons is smaller than the dimension and the number of second layer neurons. These two re…
In this paper, we consider the problem of actively learning a linear classifier through query synthesis where the learner can construct artificial queries in order to estimate the true decision boundaries. This problem has recently gained a lot of interest in automated science and adversarial reverse engineering for which only heuristic algorithms are known. In such applications, queries can be constructed de novo to elicit information (e.g., automated science) or to evade detection with minimal cost (e.g., adversarial reverse engineering). We develop a general framework, called dimension coup…
Carnegie Mellon University（卡内基梅隆大学）；IBM Almaden Research Center（IBM阿尔马登研究中心）；University of California, Berkeley（加州大学伯克利分校）
We introduce a new model of membership query (MQ) learning, where the learning algorithm is restricted to query points that are \emph{close} to random examples drawn from the underlying distribution. The learning model is intermediate between the PAC model (Valiant, 1984) and the PAC+MQ model (where the queries are allowed to be arbitrary points). Membership query algorithms are not popular among machine learning practitioners. Apart from the obvious difficulty of adaptively querying labelers, it has also been observed that querying \emph{unnatural} points leads to increased noise from human l…
Classic machine learning algorithms learn from labelled examples. For example, to design a machine translation system, a typical training set will consist of English sentences and their translation. There is a stronger model, in which the algorithm can also query for labels of new examples it creates. E.g, in the translation task, the algorithm can create a new English sentence, and request its translation from the user during training. This combination of examples and queries has been widely studied. Yet, despite many theoretical results, query algorithms are almost never used. One of the mai…
Max Planck Institute for Computer Science（马克斯·普朗克计算机科学研究所）
Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the victim model. Our work consists of two sides: We introduce sampling attack, a novel membership inference technique that unlike other standard membership adversaries is able to work under severe restriction of no access to scores of the victim model. We show that a victim model that only publishes the labels is still susceptible to sampling attacks and the adv…
The model of learning with \emph{local membership queries} interpolates between the PAC model and the membership queries model by allowing the learner to query the label of any example that is similar to an example in the training set. This model, recently proposed and studied by Awasthi, Feldman and Kanade, aims to facilitate practical use of membership queries. We continue this line of work, proving both positive and negative results in the {\em distribution free} setting. We restrict to the boolean cube $\{-1, 1\}^n$, and say that a query is $q$-local if it is of a hamming distance $\le q$ …
The explosive growth of easily-accessible unlabeled data has lead to growing interest in active learning, a paradigm in which data-hungry learning algorithms adaptively select informative examples in order to lower prohibitively expensive labeling costs. Unfortunately, in standard worst-case models of learning, the active setting often provides no improvement over non-adaptive algorithms. To combat this, a series of recent works have considered a model in which the learner may ask enriched queries beyond labels. While such models have seen success in drastically lowering label costs, they tend…
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Blueqat Research（Blueqat研究院）
Given a partition of a graph into connected components, the membership oracle asserts whether any two vertices of the graph lie in the same component or not. We prove that for $n\ge k\ge 2$, learning the components of an $n$-vertex hidden graph with $k$ components requires at least $(k-1)n-\binom k2$ membership queries. Our result improves on the best known information-theoretic bound of $Ω(n\log k)$ queries, and exactly matches the query complexity of the algorithm introduced by [Reyzin and Srivastava, 2007] for this problem. Additionally, we introduce an oracle, with access to which one can …
Oregon State University（俄勒冈州立大学）；School of Electrical Engineering and Computer Science（电气工程与计算机科学学院）
This work considers clustering nodes of a largely incomplete graph. Under the problem setting, only a small amount of queries about the edges can be made, but the entire graph is not observable. This problem finds applications in large-scale data clustering using limited annotations, community detection under restricted survey resources, and graph topology inference under hidden/removed node interactions. Prior works tackled this problem from various perspectives, e.g., convex programming-based low-rank matrix completion and active query-based clique finding. Nonetheless, many existing methods…
University of Liverpool（利物浦大学）；University of Bremen（不来梅大学）
We study the problem of learning description logic (DL) ontologies in Angluin et al.'s framework of exact learning via queries. We admit membership queries ("is a given subsumption entailed by the target ontology?") and equivalence queries ("is a given ontology equivalent to the target ontology?"). We present three main results: (1) ontologies formulated in (two relevant versions of) the description logic DL-Lite can be learned with polynomially many queries of polynomial size; (2) this is not the case for ontologies formulated in the description logic EL, even when only acyclic ontologies are…
KRDB Research Centre（KRDB研究中心）；Free University of Bozen-Bolzano（博岑-博尔扎诺自由大学）；Italy（意大利（注：此处国家信息按要求不提取，但原文中该机构位于意大利，因题目要求提取范围是机构，国家不属于机构，故仅保留机构部分）}]} 修正说明：根据提取规则，国家不属于机构，应只提取大学/学院/公司/研究院级别，因此正确应为：{）
We investigate the problem of learning description logic ontologies from entailments via queries, using epistemic reasoning. We introduce a new learning model consisting of epistemic membership and example queries and show that polynomial learnability in this model coincides with polynomial learnability in Angluin's exact learning model with membership and equivalence queries. We then instantiate our learning framework to EL and show some complexity results for an epistemic extension of EL where epistemic operators can be applied over the axioms. Finally, we transfer known results for EL ontol…
University of Kassel（卡塞尔大学）；National Research University, Higher School of Economics（高等经济学院国家研究型大学）
We propose an algorithm for learning the Horn envelope of an arbitrary domain using an expert, or an oracle, capable of answering certain types of queries about this domain. Attribute exploration from formal concept analysis is a procedure that solves this problem, but the number of queries it may ask is exponential in the size of the resulting Horn formula in the worst case. We recall a well-known polynomial-time algorithm for learning Horn formulas with membership and equivalence queries and modify it to obtain a polynomial-time probably approximately correct algorithm for learning the Horn …
Umm Al-Qura University（乌姆·古拉大学）；University of Regina（里贾纳大学）
Learning of user preferences, as represented by, for example, Conditional Preference Networks (CP-nets), has become a core issue in AI research. Recent studies investigate learning of CP-nets from randomly chosen examples or from membership and equivalence queries. To assess the optimality of learning algorithms as well as to better understand the combinatorial structure of classes of CP-nets, it is helpful to calculate certain learning-theoretic information complexity parameters. This article focuses on the frequently studied case of learning from so-called swap examples, which express prefer…
Université libre de Bruxelles（布鲁塞尔自由大学）；University of Antwerp – Flanders Make（安特卫普大学 - 弗兰德斯制造）
Active learning is a setting in which a student queries a teacher, through membership and equivalence queries, in order to learn a language. Performance on these algorithms is often measured in the number of queries required to learn a target, with an emphasis on costly equivalence queries. In graybox learning, the learning process is accelerated by foreknowledge of some information on the target. Here, we consider graybox active learning of subsequential string transducers, where a regular overapproximation of the domain is known by the student. We show that there exists an algorithm using st…
This paper establishes theoretical bonafides for implicit concurrent multivariate effect evaluation--implicit concurrency for short---a broad and versatile computational learning efficiency thought to underlie general-purpose, non-local, noise-tolerant optimization in genetic algorithms with uniform crossover (UGAs). We demonstrate that implicit concurrency is indeed a form of efficient learning by showing that it can be used to obtain close-to-optimal bounds on the time and queries required to approximately correctly solve a constrained version (k=7, η=1/5) of a recognizable computational lea…
TU Graz（格拉茨技术大学）；King’s College London（伦敦国王学院）；Ben-Gurion University（本-古里安大学）；EPFL（洛桑联邦理工学院）
We define the problem of learning a transducer ${S}$ from a target language $U$ containing possibly conflicting transducers, using membership queries and conjecture queries. The requirement is that the language of ${S}$ be a subset of $U$. We argue that this is a natural question in many situations in hardware and software verification. We devise a learning algorithm for this problem and show that its time and query complexity is polynomial with respect to the rank of the target language, its incompatibility measure, and the maximal length of a given counterexample. We report on experiments co…
SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems
ShanghaiTech University（上海科技大学）；National University of Singapore（新加坡国立大学）；Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）
