Over the years, various algorithms were developed, attempting to imitate the Human Visual System (HVS), and evaluate the perceptual image quality. However, for certain image distortions, the functionality of the HVS continues to be an enigma, and echoing its behavior remains a challenge (especially for ill-defined distortions). In this paper, we learn to compare the image quality of two registered images, with respect to a chosen distortion. Our method takes advantage of the fact that at times, simulating image distortion and later evaluating its relative image quality, is easier than assessing its absolute value. Thus, given a pair of images, we look for an optimal dimensional reduction function that will map each image to a numerical score, so that the scores will reflect the image quality relation (i.e., a less distorted image will receive a lower score). We look for an optimal dimensional reduction mapping in the form of a Deep Neural Network which minimizes the violation of image quality order. Subsequently, we extend the method to order a set of images by utilizing the predicted level of the chosen distortion. We demonstrate the validity of our method on Latent Chromatic Aberration and Moire distortions, on synthetic and real datasets.
Automatic image-based disease severity estimation generally uses discrete (i.e., quantized) severity labels. Annotating discrete labels is often difficult due to the images with ambiguous severity. An easier alternative is to use relative annotation, which compares the severity level between image pairs. By using a learning-to-rank framework with relative annotation, we can train a neural network that estimates rank scores that are relative to severity levels. However, the relative annotation for all possible pairs is prohibitive, and therefore, appropriate sample pair selection is mandatory. This paper proposes a deep Bayesian active-learning-to-rank, which trains a Bayesian convolutional neural network while automatically selecting appropriate pairs for relative annotation. We confirmed the efficiency of the proposed method through experiments on endoscopic images of ulcerative colitis. In addition, we confirmed that our method is useful even with the severe class imbalance because of its ability to select samples from minor classes automatically.
Often, the data used to train ranking models is subject to label noise. For example, in web-search, labels created from clickstream data are noisy due to issues such as insufficient information in item descriptions on the SERP, query reformulation by the user, and erratic or unexpected user behavior. In practice, it is difficult to handle label noise without making strong assumptions about the label generation process. As a result, practitioners typically train their learning-to-rank (LtR) models directly on this noisy data without additional consideration of the label noise. Surprisingly, we often see strong performance from LtR models trained in this way. In this work, we describe a class of noise-tolerant LtR losses for which empirical risk minimization is a consistent procedure, even in the context of class-conditional label noise. We also develop noise-tolerant analogs of commonly used loss functions. The practical implications of our theoretical findings are further supported by experimental results.
Context: Recent research indicates that Web queries written by software developers are not very successful in retrieving relevant results, performing measurably worse compared to general purpose Web queries. Most approaches up to this point have addressed this problem with software engineering-specific automated query reformulation techniques, which work without developer involvement but are limited by the content of the original query. In other words, these techniques automatically improve the existing query but can not contribute new, previously unmentioned, concepts. Objective: In this paper, we propose a technique to guide software developers in manually improving their own Web search queries. We examine a conversational approach that follows unsuccessful queries with a clarification question aimed at eliciting additional query terms, thus providing to the developer a clear dimension along which the query could be improved. Methods: We describe a set of clarification questions derived from a corpus of software developer queries and a neural approach to recommending them for a newly issued query. Results: Our evaluation indicates that the recommendation technique is accurate, predicting a valid clarification question 80% of the time and outperforms simple baselines, as well as, state-of-the-art Learning To Rank (LTR) baselines. Conclusion: As shown in the experimental results, the described approach is capable at recommending appropriate clarification questions to software developers and considered useful by a sample of developers ranging from novices to experienced professionals.
People leverage group discussions to collaborate in order to solve complex tasks, e.g. in project meetings or hiring panels. By doing so, they engage in a variety of conversational strategies where they try to convince each other of the best approach and ultimately reach a decision. In this work, we investigate methods for detecting what makes someone change their mind. To this end, we leverage a recently introduced dataset containing group discussions of people collaborating to solve a task. To find out what makes someone change their mind, we incorporate various techniques such as neural text classification and language-agnostic change point detection. Evaluation of these methods shows that while the task is not trivial, the best way to approach it is using a language-aware model with learning-to-rank training. Finally, we examine the cues that the models develop as indicative of the cause of a change of mind.
Unbiased Learning to Rank (ULTR) that learns to rank documents with biased user feedback data is a well-known challenge in information retrieval. Existing methods in unbiased learning to rank typically rely on click modeling or inverse propensity weighting (IPW). Unfortunately, the search engines are faced with severe long-tail query distribution, where neither click modeling nor IPW can handle well. Click modeling suffers from data sparsity problem since the same query-document pair appears limited times on tail queries; IPW suffers from high variance problem since it is highly sensitive to small propensity score values. Therefore, a general debiasing framework that works well under tail queries is in desperate need. To address this problem, we propose a model-based unbiased learning-to-rank framework. Specifically, we develop a general context-aware user simulator to generate pseudo clicks for unobserved ranked lists to train rankers, which addresses the data sparsity problem. In addition, considering the discrepancy between pseudo clicks and actual clicks, we take the observation of a ranked list as the treatment variable and further incorporate inverse propensity weighting with pseudo labels in a doubly robust way. The derived bias and variance indicate that the proposed model-based method is more robust than existing methods. Finally, extensive experiments on benchmark datasets, including simulated datasets and real click logs, demonstrate that the proposed model-based method consistently performs outperforms state-of-the-art methods in various scenarios. The code is available at https://github.com/rowedenny/MULTR.
Pairwise debiasing is one of the most effective strategies in reducing position bias in learning-to-rank (LTR) models. However, limiting the scope of this strategy, are the underlying assumptions required by many pairwise debiasing approaches. In this paper, we develop an approach based on a minimalistic set of assumptions that can be applied to a much broader range of user browsing patterns and arbitrary presentation layouts. We implement the approach as a simplified version of the Unbiased LambdaMART and demonstrate that it retains the underlying unbiasedness property in a wider variety of settings than the original algorithm. Finally, using simulations with "golden" relevance labels, we will show that the simplified version compares favourably with the original Unbiased LambdaMART when the examination of different positions in a ranked list is not assumed to be independent.
Online learning to rank (OLTR) interactively learns to choose lists of items from a large collection based on certain click models that describe users' click behaviors. Most recent works for this problem focus on the stochastic environment where the item attractiveness is assumed to be invariant during the learning process. In many real-world scenarios, however, the environment could be dynamic or even arbitrarily changing. This work studies the OLTR problem in both stochastic and adversarial environments under the position-based model (PBM). We propose a method based on the follow-the-regularized-leader (FTRL) framework with Tsallis entropy and develop a new self-bounding constraint especially designed for PBM. We prove the proposed algorithm simultaneously achieves $O(\log{T})$ regret in the stochastic environment and $O(m\sqrt{nT})$ regret in the adversarial environment, where $T$ is the number of rounds, $n$ is the number of items and $m$ is the number of positions. We also provide a lower bound of order $\Omega(m\sqrt{nT})$ for adversarial PBM, which matches our upper bound and improves over the state-of-the-art lower bound. The experiments show that our algorithm could simultaneously learn in both stochastic and adversarial environments and is competitive compared to existing methods that are designed for a single environment.
Learning to Rank (LTR) technique is ubiquitous in the Information Retrieval system nowadays, especially in the Search Ranking application. The query-item relevance labels typically used to train the ranking model are often noisy measurements of human behavior, e.g., product rating for product search. The coarse measurements make the ground truth ranking non-unique with respect to a single relevance criterion. To resolve ambiguity, it is desirable to train a model using many relevance criteria, giving rise to Multi-Label LTR (MLLTR). Moreover, it formulates multiple goals that may be conflicting yet important to optimize for simultaneously, e.g., in product search, a ranking model can be trained based on product quality and purchase likelihood to increase revenue. In this research, we leverage the Multi-Objective Optimization (MOO) aspect of the MLLTR problem and employ recently developed MOO algorithms to solve it. Specifically, we propose a general framework where the information from labels can be combined in a variety of ways to meaningfully characterize the trade-off among the goals. Our framework allows for any gradient based MOO algorithm to be used for solving the MLLTR problem. We test the proposed framework on two publicly available LTR datasets and one e-commerce dataset to show its efficacy.
The unbiased learning to rank (ULTR) problem has been greatly advanced by recent deep learning techniques and well-designed debias algorithms. However, promising results on the existing benchmark datasets may not be extended to the practical scenario due to the following disadvantages observed from those popular benchmark datasets: (1) outdated semantic feature extraction where state-of-the-art large scale pre-trained language models like BERT cannot be exploited due to the missing of the original text;(2) incomplete display features for in-depth study of ULTR, e.g., missing the displayed abstract of documents for analyzing the click necessary bias; (3) lacking real-world user feedback, leading to the prevalence of synthetic datasets in the empirical study. To overcome the above disadvantages, we introduce the Baidu-ULTR dataset. It involves randomly sampled 1.2 billion searching sessions and 7,008 expert annotated queries, which is orders of magnitude larger than the existing ones. Baidu-ULTR provides:(1) the original semantic feature and a pre-trained language model for easy usage; (2) sufficient display information such as position, displayed height, and displayed abstract, enabling the comprehensive study of different biases with advanced techniques such as causal discovery and meta-learning; and (3) rich user feedback on search result pages (SERPs) like dwelling time, allowing for user engagement optimization and promoting the exploration of multi-task learning in ULTR. In this paper, we present the design principle of Baidu-ULTR and the performance of benchmark ULTR algorithms on this new data resource, favoring the exploration of ranking for long-tail queries and pre-training tasks for ranking. The Baidu-ULTR dataset and corresponding baseline implementation are available at https://github.com/ChuXiaokai/baidu_ultr_dataset.
When building recommendation systems, we seek to output a helpful set of items to the user. Under the hood, a ranking model predicts which of two candidate items is better, and we must distill these pairwise comparisons into the user-facing output. However, a learned ranking model is never perfect, so taking its predictions at face value gives no guarantee that the user-facing output is reliable. Building from a pre-trained ranking model, we show how to return a set of items that is rigorously guaranteed to contain mostly good items. Our procedure endows any ranking model with rigorous finite-sample control of the false discovery rate (FDR), regardless of the (unknown) data distribution. Moreover, our calibration algorithm enables the easy and principled integration of multiple objectives in recommender systems. As an example, we show how to optimize for recommendation diversity subject to a user-specified level of FDR control, circumventing the need to specify ad hoc weights of a diversity loss against an accuracy loss. Throughout, we focus on the problem of learning to rank a set of possible recommendations, evaluating our methods on the Yahoo! Learning to Rank and MSMarco datasets.
Over the past decades, researchers had put lots of effort investigating ranking techniques used to rank query results retrieved during information retrieval, or to rank the recommended products in recommender systems. In this project, we aim to investigate searching, ranking, as well as recommendation techniques to help to realize a university academia searching platform. Unlike the usual information retrieval scenarios where lots of ground truth ranking data is present, in our case, we have only limited ground truth knowledge regarding the academia ranking. For instance, given some search queries, we only know a few researchers who are highly relevant and thus should be ranked at the top, and for some other search queries, we have no knowledge about which researcher should be ranked at the top at all. The limited amount of ground truth data makes some of the conventional ranking techniques and evaluation metrics become infeasible, and this is a huge challenge we faced during this project. This project enhances the user's academia searching experience to a large extent, it helps to achieve an academic searching platform which includes researchers, publications and fields of study information, which will be beneficial not only to the university faculties but also to students' research experiences.
Efficient search is a critical component for an e-commerce platform with an innumerable number of products. Every day millions of users search for products pertaining to their needs. Thus, showing the relevant products on the top will enhance the user experience. In this work, we propose a novel approach of fusing a transformer-based model with various listwise loss functions for ranking e-commerce products, given a user query. We pre-train a RoBERTa model over a fashion e-commerce corpus and fine-tune it using different listwise loss functions. Our experiments indicate that the RoBERTa model fine-tuned with an NDCG based surrogate loss function(approxNDCG) achieves an NDCG improvement of 13.9% compared to other popular listwise loss functions like ListNET and ListMLE. The approxNDCG based RoBERTa model also achieves an NDCG improvement of 20.6% compared to the pairwise RankNet based RoBERTa model. We call our methodology of directly optimizing the RoBERTa model in an end-to-end manner with a listwise surrogate loss function as ListBERT. Since there is a low latency requirement in a real-time search setting, we show how these models can be easily adopted by using a knowledge distillation technique to learn a representation-focused student model that can be easily deployed and leads to ~10 times lower ranking latency.
Who should we prioritize for intervention when we cannot estimate intervention effects? In many applied domains -- such as advertising, customer retention, and behavioral nudging -- prioritization is guided by predictive models that estimate outcome probabilities rather than causal effects. This paper investigates when these predictions (scores) can effectively rank individuals by their intervention effects, particularly when direct effect estimation is infeasible or unreliable. We propose a conceptual framework based on amenability -- an individual's latent proclivity to be influenced by an intervention -- and formalize conditions under which predictive scores serve as effective proxies for amenability. These conditions justify using non-causal scores for intervention prioritization, even when the scores do not directly estimate effects. We further show that, under plausible assumptions, predictive models can outperform causal effect estimators in ranking individuals by intervention effects. Empirical evidence from an advertising context supports our theoretical findings, demonstrating that predictive modeling can offer a more robust approach to targeting than effect estimation. Our framework suggests a shift in focus -- from estimating effects to inferring who is amenable -- as a practical and theoretically grounded strategy for prioritizing interventions in resource-constrained environments.
Click-based learning to rank (LTR) tackles the mismatch between click frequencies on items and their actual relevance. The approach of previous work has been to assume a model of click behavior and to subsequently introduce a method for unbiasedly estimating preferences under that assumed model. The success of this approach is evident in that unbiased methods have been found for an increasing number of behavior models and types of bias. This work aims to uncover the implicit limitations of the high-level prevalent approach in the counterfactual LTR field. Thus, in contrast with limitations that follow from explicit assumptions, our aim is to recognize limitations that the field is currently unaware of. We do this by inverting the existing approach: we start by capturing existing methods in generic terms, and subsequently, from these generic descriptions we derive the click behavior for which these methods can be unbiased. Our inverted approach reveals that there are indeed implicit limitations to the counterfactual LTR approach: we find counterfactual estimation can only produce unbiased methods for click behavior based on affine transformations. In addition, we also recognize previously undiscussed limitations of click-modelling and pairwise approaches to click-based LTR. Our findings reveal that it is impossible for existing approaches to provide unbiasedness guarantees for all plausible click behavior models.
The intersection of learning to rank and choice modeling is an active area of research with applications in e-commerce, information retrieval and the social sciences. In some applications such as recommendation systems, the statistician is primarily interested in recovering the set of the top ranked items from a large pool of items as efficiently as possible using passively collected discrete choice data, i.e., the user picks one item from a set of multiple items. Motivated by this practical consideration, we propose the choice-based Borda count algorithm as a fast and accurate ranking algorithm for top $K$-recovery i.e., correctly identifying all of the top $K$ items. We show that the choice-based Borda count algorithm has optimal sample complexity for top-$K$ recovery under a broad class of random utility models. We prove that in the limit, the choice-based Borda count algorithm produces the same top-$K$ estimate as the commonly used Maximum Likelihood Estimate method but the former's speed and simplicity brings considerable advantages in practice. Experiments on both synthetic and real datasets show that the counting algorithm is competitive with commonly used ranking algorithms in terms of accuracy while being several orders of magnitude faster.
FOLD-R++ is a new inductive learning algorithm for binary classification tasks. It generates an (explainable) normal logic program for mixed type (numerical and categorical) data. We present a customized FOLD-R++ algorithm with the ranking framework, called FOLD-TR, that aims to rank new items following the ranking pattern in the training data. Like FOLD-R++, the FOLD-TR algorithm is able to handle mixed-type data directly and provide native justification to explain the comparison between a pair of items.
Deep neural networks (DNNs) demonstrate significant advantages in improving ranking performance in retrieval tasks. Driven by the recent technical developments in optimization and generalization of DNNs, learning a neural ranking model online from its interactions with users becomes possible. However, the required exploration for model learning has to be performed in the entire neural network parameter space, which is prohibitively expensive and limits the application of such online solutions in practice. In this work, we propose an efficient exploration strategy for online interactive neural ranker learning based on the idea of bootstrapping. Our solution employs an ensemble of ranking models trained with perturbed user click feedback. The proposed method eliminates explicit confidence set construction and the associated computational overhead, which enables the online neural rankers' training to be efficiently executed in practice with theoretical guarantees. Extensive comparisons with an array of state-of-the-art OL2R algorithms on two public learning to rank benchmark datasets demonstrate the effectiveness and computational efficiency of our proposed neural OL2R solution.
State-of-the-art recommender system (RS) mostly rely on complex deep neural network (DNN) model structure, which makes it difficult to provide explanations along with RS decisions. Previous researchers have proved that providing explanations along with recommended items can help users make informed decisions and improve their trust towards the uninterpretable blackbox system. In model-agnostic explainable recommendation, system designers deploy a separate explanation model to take as input from the decision model, and generate explanations to meet the goal of persuasiveness. In this work, we explore the task of ranking textual rationales (supporting evidences) for model-agnostic explainable recommendation. Most of existing rationales ranking algorithms only utilize the rationale IDs and interaction matrices to build latent factor representations; and the semantic information within the textual rationales are not learned effectively. We argue that such design is suboptimal as the important semantic information within the textual rationales may be used to better profile user preferences and item features. Seeing this gap, we propose a model named Semantic-Enhanced Bayesian Personalized Explanation Ranking (SE-BPER) to effectively combine the interaction information and semantic information. SE-BPER first initializes the latent factor representations with contextualized embeddings generated by transformer model, then optimizes them with the interaction data. Extensive experiments show that such methodology improves the rationales ranking performance while simplifying the model training process (fewer hyperparameters and faster convergence). We conclude that the optimal way to combine semantic and interaction information remains an open question in the task of rationales ranking.
Search engines and recommendation systems attempt to continually improve the quality of the experience they afford to their users. Refining the ranker that produces the lists displayed in response to user requests is an important component of this process. A common practice is for the service providers to make changes (e.g. new ranking features, different ranking models) and A/B test them on a fraction of their users to establish the value of the change. An alternative approach estimates the effectiveness of the proposed changes offline, utilising previously collected clickthrough data on the old ranker to posit what the user behaviour on ranked lists produced by the new ranker would have been. A majority of offline evaluation approaches invoke the well studied inverse propensity weighting to adjust for biases inherent in logged data. In this paper, we propose the use of parametric estimates for these propensities. Specifically, by leveraging well known learning-to-rank methods as subroutines, we show how accurate offline evaluation can be achieved when the new rankings to be evaluated differ from the logged ones.