Recent papers have shown that sufficiently overparameterized neural networks can perfectly fit even random labels. Thus, it is crucial to understand the underlying reason behind the generalization performance of a network on real-world data. In this work, we propose several measures to predict the generalization error of a network given the training data and its parameters. Using one of these measures, based on noise resilience of the network, we secured 5th position in the predicting generalization in deep learning (PGDL) competition at NeurIPS 2020.
Learning to rank is a supervised learning problem where the output space is the space of rankings but the supervision space is the space of relevance scores. We make theoretical contributions to the learning to rank problem both in the online and batch settings. First, we propose a perceptron-like algorithm for learning a ranking function in an online setting. Our algorithm is an extension of the classic perceptron algorithm for the classification problem. Second, in the setting of batch learning, we introduce a sufficient condition for convex ranking surrogates to ensure a generalization boun…
(Partial) ranking loss is a commonly used evaluation measure for multi-label classification, which is usually optimized with convex surrogates for computational efficiency. Prior theoretical work on multi-label ranking mainly focuses on (Fisher) consistency analyses. However, there is a gap between existing theory and practice -- some pairwise losses can lead to promising performance but lack consistency, while some univariate losses are consistent but usually have no clear superiority in practice. In this paper, we attempt to fill this gap through a systematic study from two complementary per…
Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for AI（博世人工智能中心）
The ability of overparameterized deep networks to generalize well has been linked to the fact that stochastic gradient descent (SGD) finds solutions that lie in flat, wide minima in the training loss -- minima where the output of the network is resilient to small random noise added to its parameters. So far this observation has been used to provide generalization guarantees only for neural networks whose parameters are either \textit{stochastic} or \textit{compressed}. In this work, we present a general PAC-Bayesian framework that leverages this observation to provide a bound on the original n…
We consider the problem of learning the true ordering of a set of alternatives from largely incomplete and noisy rankings. We introduce a natural generalization of both the classical Mallows model of ranking distributions and the extensively studied model of noisy pairwise comparisons. Our selective Mallows model outputs a noisy ranking on any given subset of alternatives, based on an underlying Mallows distribution. Assuming a sequence of subsets where each pair of alternatives appears frequently enough, we obtain strong asymptotically tight upper and lower bounds on the sample complexity of …
Bipartite ranking is an important supervised learning problem; however, unlike regression or classification, it has a quadratic dependence on the number of samples. To circumvent the prohibitive sample cost, many recent work focus on stochastic gradient-based methods. In this paper we consider an alternative approach, which leverages the structure of the widely-adopted pairwise squared loss, to obtain a stochastic and low cost algorithm that does not require stochastic gradients or learning rates. Using a novel uniform risk bound---based on matrix and vector concentration inequalities---we sho…
National University of Singapore（新加坡国立大学）；MIT（麻省理工学院）
This paper presents a novel approach to top-$k$ ranking Bayesian optimization (top-$k$ ranking BO) which is a practical and significant generalization of preferential BO to handle top-$k$ ranking and tie/indifference observations. We first design a surrogate model that is not only capable of catering to the above observations, but is also supported by a classic random utility model. Another equally important contribution is the introduction of the first information-theoretic acquisition function in BO with preferential observation called multinomial predictive entropy search (MPES) which is fl…
Xi’an Jiaotong University（西安交通大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Technology Sydney（悉尼科技大学）；National University of Singapore（新加坡国立大学）
The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval. Some studies formalize the cross-modal retrieval tasks as a ranking problem and learn a shared multi-modal embedding space to measure the cross-modality similarity. However, previous methods often establish the shared embedding space based on linear mapping functions which might not be sophisticated enough to reveal more complicated inter-modal correspondences. Additionally, current studies assume that the rankings are of equal importance, and thus all rankings are used simult…
In this paper we consider the collaborative ranking setting: a pool of users each provides a small number of pairwise preferences between $d$ possible items; from these we need to predict preferences of the users for items they have not yet seen. We do so by fitting a rank $r$ score matrix to the pairwise data, and provide two main contributions: (a) we show that an algorithm based on convex optimization provides good generalization guarantees once each user provides as few as $O(r\log^2 d)$ pairwise comparisons -- essentially matching the sample complexity required in the related matrix compl…
Laboratoire d’Informatique Fondamentale de Marseille（马赛基础信息学实验室）；CNRS（法国国家科学研究中心）
Pac-Bayes bounds are among the most accurate generalization bounds for classifiers learned from independently and identically distributed (IID) data, and it is particularly so for margin classifiers: there have been recent contributions showing how practical these bounds can be either to perform model selection (Ambroladze et al., 2007) or even to directly guide the learning of linear classifiers (Germain et al., 2009). However, there are many practical situations where the training data show some dependencies and where the traditional IID assumption does not hold. Stating generalization bound…
LTCI, Télécom Paris, Institut Polytechnique de Paris（LTCI、巴黎电信学院、巴黎综合理工学院）；INRIA（法国国家信息与自动化研究所）
Many applications of AI involve scoring individuals using a learned function of their attributes. These predictive risk scores are then used to take decisions based on whether the score exceeds a certain threshold, which may vary depending on the context. The level of delegation granted to such systems in critical applications like credit lending and medical diagnosis will heavily depend on how questions of fairness can be answered. In this paper, we study fairness for the problem of learning scoring functions from binary labeled data, a classic learning task known as bipartite ranking. We arg…
Sensetime Research Group（商汤科技研究组）；Beihang University（北京航空航天大学）；The University of Sydney（悉尼大学）
Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some recent influential attempts would like to adaptively control the parameter-wise learning rate (e.g., Adam and RMSProp). Although they show a large improvement in convergence speed, most adaptive learning rate methods suffer from compromised generalization compared with SGD. In this paper, we proposed an Adaptive Gradient Method with Resilience and Momentum (AdaRem), motivated by the observation that the oscillations o…
Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification
IIE, Chinese Academy of Sciences（中国科学院自动化研究所）；SCS, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；IIP, ICT, Chinese Academy of Sciences（中国科学院计算技术研究所）；SCST, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Alibaba Group（阿里巴巴集团）；SCST, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区计算机科学与技术学院）；BDKM, University of Chinese Academy of Sciences（中国科学院大学大数据与知识管理实验室）
Nanjing University（南京大学）；Michigan State University（密歇根州立大学）
Bipartite ranking aims to learn a real-valued ranking function that orders positive instances before negative instances. Recent efforts of bipartite ranking are focused on optimizing ranking accuracy at the top of the ranked list. Most existing approaches are either to optimize task specific metrics or to extend the ranking loss by emphasizing more on the error associated with the top ranked instances, leading to a high computational cost that is super-linear in the number of training instances. We propose a highly efficient approach, titled TopPush, for optimizing accuracy at the top that has…
We consider the generalization ability of algorithms for learning to rank at a query level, a problem also called subset ranking. Existing generalization error bounds necessarily degrade as the size of the document list associated with a query increases. We show that such a degradation is not intrinsic to the problem. For several loss functions, including the cross-entropy loss used in the well known ListNet method, there is \emph{no} degradation in generalization ability as document lists become longer. We also provide novel generalization error bounds under $\ell_1$ regularization and faster…
The ROC curve is the gold standard for measuring the performance of a test/scoring statistic regarding its capacity to discriminate between two statistical populations in a wide variety of applications, ranging from anomaly detection in signal processing to information retrieval, through medical diagnosis. Most practical performance measures used in scoring/ranking applications such as the AUC, the local AUC, the p-norm push, the DCG and others, can be viewed as summaries of the ROC curve. In this paper, the fact that most of these empirical criteria can be expressed as two-sample linear rank …
NDCG-Consistent Softmax Approximation with Accelerated Convergence
School of Artificial Intelligence & Data Science University of Science and Technology of China（人工智能与数据科学学院 中国科学技术大学）；School of Computer Science & Technology University of Science and Technology of China（计算机科学与技术学院 中国科学技术大学）；School of Business & Management Hong Kong University of Science and Technology（管理学院 香港科学与技术大学）
本文通过 Taylor 展开提出与排序指标对齐的 RG² 与 RG^× 损失，并结合 ALS 优化，在保证排序性能的同时显著提升大规模相似度学习的收敛效率。
This paper aims at formulating the issue of ranking multivariate unlabeled observations depending on their degree of abnormality as an unsupervised statistical learning task. In the 1-d situation, this problem is usually tackled by means of tail estimation techniques: univariate observations are viewed as all the more `abnormal' as they are located far in the tail(s) of the underlying probability distribution. It would be desirable as well to dispose of a scalar valued `scoring' function allowing for comparing the degree of abnormality of multivariate observations. Here we formulate the issue …
IMT Atlantique（IMT大西洋高等矿业电信学院）；Université Fédérale de Toulouse（图卢兹联邦大学）
Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task. In this work, we propose exploiting Latent Geometry Graphs (LGGs) to represent the latent spaces of trained DNN architectures. Such graphs are obtained by connecting samples that yield similar latent representations at a given layer of the considered DNN. We then obtain a generalization score by looking at how strongly connected are samples of distinct classes in LGGs. This score allowed us to rank 3rd on the NeurIPS 2020 Predicting Generalization in Deep Learning (P…
DeepMind（深度思维）；Google（谷歌）；The Chinese University of Hong Kong（香港中文大学）；University of Alberta（阿尔伯塔大学）
Online learning to rank is a sequential decision-making problem where in each round the learning agent chooses a list of items and receives feedback in the form of clicks from the user. Many sample-efficient algorithms have been proposed for this problem that assume a specific click model connecting rankings and user behavior. We propose a generalized click model that encompasses many existing models, including the position-based and cascade models. Our generalization motivates a novel online learning algorithm based on topological sort, which we call TopRank. TopRank is (a) more natural than …
We consider the problem of learning over non-stationary ranking streams. The rankings can be interpreted as the preferences of a population and the non-stationarity means that the distribution of preferences changes over time. Our goal is to learn, in an online manner, the current distribution of rankings. The bottleneck of this process is a rank aggregation problem. We propose a generalization of the Borda algorithm for non-stationary ranking streams. Moreover, we give bounds on the minimum number of samples required to output the ground truth with high probability. Besides, we show how the o…
In domains like bioinformatics, information retrieval and social network analysis, one can find learning tasks where the goal consists of inferring a ranking of objects, conditioned on a particular target object. We present a general kernel framework for learning conditional rankings from various types of relational data, where rankings can be conditioned on unseen data objects. We propose efficient algorithms for conditional ranking by optimizing squared regression and ranking loss functions. We show theoretically, that learning with the ranking loss is likely to generalize better than with t…
Despite their empirical success, most existing listwiselearning-to-rank (LTR) models are not built to be robust to errors in labeling or annotation, distributional data shift, or adversarial data perturbations. To fill this gap, we introduce a new listwise LTR model called Distributionally Robust Multi-output Regression Ranking (DRMRR). Different from existing methods, the scoring function of DRMRR was designed as a multivariate mapping from a feature vector to a vector of deviation scores, which captures local context information and cross-document interactions. DRMRR uses a Distributionally …
Adversarial training is an approach for increasing model's resilience against adversarial perturbations. Such approaches have been demonstrated to result in models with feature representations that generalize better. However, limited works have been done on adversarial training of models on graph data. In this paper, we raise such a question { does adversarial training improve the generalization of graph representations. We formulate L2 and L1 versions of adversarial training in two powerful node embedding methods: graph autoencoder (GAE) and variational graph autoencoder (VGAE). We conduct ex…
As one of the most popular techniques for solving the ranking problem in information retrieval, Learning-to-rank (LETOR) has received a lot of attention both in academia and industry due to its importance in a wide variety of data mining applications. However, most of existing LETOR approaches choose to learn a single global ranking function to handle all queries, and ignore the substantial differences that exist between queries. In this paper, we propose a domain generalization strategy to tackle this problem. We propose Query-Invariant Listwise Context Modeling (QILCM), a novel neural archit…
The concept of median/consensus has been widely investigated in order to provide a statistical summary of ranking data, i.e. realizations of a random permutation $Σ$ of a finite set, $\{1,\; \ldots,\; n\}$ with $n\geq 1$ say. As it sheds light onto only one aspect of $Σ$'s distribution $P$, it may neglect other informative features. It is the purpose of this paper to define analogs of quantiles, ranks and statistical procedures based on such quantities for the analysis of ranking data by means of a metric-based notion of depth function on the symmetric group. Overcoming the absence of vector s…
The Netherlands Organization for Applied Scientific Research（荷兰应用科学研究组织）；Radboud University Nijmegen（奈梅亨拉德堡德大学）
We propose a novel sparse preference learning/ranking algorithm. Our algorithm approximates the true utility function by a weighted sum of basis functions using the squared loss on pairs of data points, and is a generalization of the kernel matching pursuit method. It can operate both in a supervised and a semi-supervised setting and allows efficient search for multiple, near-optimal solutions. Furthermore, we describe the extension of the algorithm suitable for combined ranking and regression tasks. In our experiments we demonstrate that the proposed algorithm outperforms several state-of-the…
Given the abundance of applications of ranking in recent years, addressing fairness concerns around automated ranking systems becomes necessary for increasing the trust among end-users. Previous work on fair ranking has mostly focused on application-specific fairness notions, often tailored to online advertising, and it rarely considers learning as part of the process. In this work, we show how to transfer numerous fairness notions from binary classification to a learning to rank setting. Our formalism allows us to design methods for incorporating fairness objectives with provable generalizati…
Radboud University（拉德堡德大学）；University of Amsterdam（阿姆斯特丹大学）；Ahold Delhaize（皇家阿霍德德尔海兹集团）
Existing work in counterfactual Learning to Rank (LTR) has focussed on optimizing feature-based models that predict the optimal ranking based on document features. LTR methods based on bandit algorithms often optimize tabular models that memorize the optimal ranking per query. These types of model have their own advantages and disadvantages. Feature-based models provide very robust performance across many queries, including those previously unseen, however, the available features often limit the rankings the model can predict. In contrast, tabular models can converge on any possible ranking th…
AbRank: A Benchmark Dataset and Metric-Learning Framework for Antibody-Antigen Affinity Ranking
Structural Molecular Biology, Division of Biosciences, University College London（伦敦大学学院生物结构分子生物学系）；Institute of Computational Life Sciences, Zürich University of Applied Sciences (ZHAW)（苏黎世应用科学大学计算生命科学研究所）；Biomedical Informatics and Data Science, Yale School of Medicine（耶鲁医学院生物医学信息学与数据科学）；Centre for Artificial Intelligence, University College London（伦敦大学学院人工智能中心）
GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models
Department of Computing, The Hong Kong Polytechnic University, Hong Kong（香港理工大学计算机系）；School of Artificial Intelligence and Data Science, IIT Jodhpur（IIT朱罗浦人工智能与数据科学学院）
Columbia University（哥伦比亚大学）；Stanford University（斯坦福大学）；ASAPP（ASAPP公司）；Cornell University（康奈尔大学）
Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled. This paper introduces a new method to identify such samples and mitigate their impact when training neural networks. At the heart of our algorithm is the Area Under the Margin (AUM) statistic, which exploits differences in the training dynamics of clean and mislabeled samples. A simple procedure - adding an extra class populated with purposefully mislabeled threshold samples - learns a AUM upper bound that isolates mislabeled data. This approach consistently improves …
Yale University（耶鲁大学）；Indian Institute of Technology, Kanpur（坎pur印度理工学院）
Implicit bias is the unconscious attribution of particular qualities (or lack thereof) to a member from a particular social group (e.g., defined by gender or race). Studies on implicit bias have shown that these unconscious stereotypes can have adverse outcomes in various social contexts, such as job screening, teaching, or policing. Recently, (Kleinberg and Raghavan, 2018) considered a mathematical model for implicit bias and showed the effectiveness of the Rooney Rule as a constraint to improve the utility of the outcome for certain cases of the subset selection problem. Here we study the pr…
University of Virginia（弗吉尼亚大学）；Google Research（谷歌研究院）
Multiclass classification (MCC) is a fundamental machine learning problem of classifying each instance into one of a predefined set of classes. In the deep learning era, extensive efforts have been spent on developing more powerful neural embedding models to better represent the instance for improving MCC performance. In this paper, we do not aim to propose new neural models for instance representation learning, but to show that it is promising to boost MCC performance with a novel formulation through the lens of ranking. In particular, by viewing MCC as to rank classes for an instance, we fir…
This paper studies the consistency of the kernel-based neural ranking model K-NRM, a recent state-of-the-art neural IR model, which is important for reproducible research and deployment in the industry. We find that K-NRM has low variance on relevance-based metrics across experimental trials. In spite of this low variance in overall performance, different trials produce different document rankings for individual queries. The main source of variance in our experiments was found to be different latent matching patterns captured by K-NRM. In the IR-customized word embeddings learned by K-NRM, the…
To improve model generalization, model designers often restrict the features that their models use, either implicitly or explicitly. In this work, we explore the design space of leveraging such feature priors by viewing them as distinct perspectives on the data. Specifically, we find that models trained with diverse sets of feature priors have less overlapping failure modes, and can thus be combined more effectively. Moreover, we demonstrate that jointly training such models on additional (unlabeled) data allows them to correct each other's mistakes, which, in turn, leads to better generalizat…
University of Science and Technology of China（中国科学技术大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Most recommender systems optimize the model on observed interaction data, which is affected by the previous exposure mechanism and exhibits many biases like popularity bias. The loss functions, such as the mostly used pointwise Binary Cross-Entropy and pairwise Bayesian Personalized Ranking, are not designed to consider the biases in observed data. As a result, the model optimized on the loss would inherit the data biases, or even worse, amplify the biases. For example, a few popular items take up more and more exposure opportunities, severely hurting the recommendation quality on niche items …
InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search
School of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）；School of Computer and Data Science, Minjiang University（闽江学院计算机与数据科学学院）；School of Artificial Intelligence, Nanchang University（南昌大学人工智能学院）；Department of Computer Science, Hong Kong Baptist University（香港浸会大学计算机科学系）；School of Interdisciplinary Medicine and Engineering, Harbin Medical University（哈尔滨医科大学跨学科医学与工程学院）
