Given historical traffic distributions and associated urban conditions observed in a city, the conditional urban traffic estimation problem aims at estimating realistic future projections of the traffic under a set of new urban conditions, e.g., new bus routes, rainfall intensity, and travel demands. The problem is important in reducing traffic congestion, improving public transportation efficiency, and facilitating urban planning. However, solving this problem is challenging due to the strong spatial dependencies of traffic patterns and the complex relations between the traffic and urban conditions. Recently, we proposed a Complex-Condition-Controlled Generative Adversarial Network ( \(\boldsymbol{C^{3}}\) -GAN) , which tackles both of the challenges and solves the urban traffic estimation problem under various complex conditions by adding a fixed embedding network and an inference network on top of the standard conditional GAN model. The randomly chosen embedding network transforms the complex conditions to latent vectors, and the inference network enhances the connections between the embedded vectors and the traffic data. However, a randomly chosen embedding network cannot always successfully extract features of complex urban conditions, which indicates \(C^{3}\) -GAN is unable to uniquely map different urban conditions to proper latent distributions. Thus, \(C^{3}\) -GAN would fail in certain traffic estimation tasks. Besides, \(C^{3}\) -GAN is hard to train due to vanishing gradients and mode collapse problems. To address these issues, in this article, we extend our prior work by introducing a new deep generative model, namely, \(C^{3}\) -GAN \(+\) , which significantly improves the estimation performance and model stability. \(C^{3}\) -GAN \(+\) has new objective, architecture, and training algorithm. The new objective applies Wasserstein loss to the conditional generation case to encourage stable training. Shared convolutional layers between the discriminator and the inference network help to capture spatial dependencies of traffic more efficiently, part of the shared convolutional layers are used to update the embedding network periodically aiming to encourage good representation and avoid model divergence. Extensive experiments on real-world datasets demonstrate that our \(C^{3}\) -GAN \(+\) produces high-quality traffic estimations and outperforms state-of-the-art baseline methods.

Personalized recommender systems play a crucial role in modern society, especially in e-commerce, news, and ads areas. Correctly evaluating and comparing candidate recommendation models is as essential as constructing ones. The common offline evaluation strategy is holding out some user-interacted items from training data and evaluating the performance of recommendation models based on how many items they can retrieve. Specifically, for any hold-out item or so-called target item for a user, the recommendation models try to predict the probability that the user would interact with the item and rank it among overall items, which is called global evaluation . Intuitively, a good recommendation model would assign high probabilities to such hold-out/target items. Based on the specific ranks, some metrics like Recall@K and NDCG@K can be calculated to further quantify the quality of the recommender model. Instead of ranking the target items among all items, Koren first proposed to rank them among a small sampled set of items , then quantified the performance of the models, which is called sampling evaluation . Ever since then, there has been a large amount of work adopting sampling evaluation due to its efficiency and frugality. In recent work, Rendle and Krichene argued that the sampling evaluation is “inconsistent” with respect to a global evaluation in terms of offline top- K metrics. In this work, we first investigate the “inconsistent” phenomenon by taking a glance at the connections between sampling evaluation and global evaluation. We reveal the approximately linear relationship between sampling with respect to its global counterpart in terms of the top- K Recall metric. Second, we propose a new statistical perspective of the sampling evaluation—to estimate the global rank distribution of the entire population. After the estimated rank distribution is obtained, the approximation of the global metric can be further derived. Third, we extend the work of Krichene and Rendle, directly optimizing the error with ground truth, providing not only a comprehensive empirical study but also a rigorous theoretical understanding of the proposed metric estimators. To address the “blind spot” issue, where accurately estimating metrics for small top- K values in sampling evaluation is challenging, we propose a novel adaptive sampling method that generalizes the expectation-maximization algorithm to this setting. Last but not least, we also study the user sampling evaluation effect. This series of works outlines a clear roadmap for sampling evaluation and establishes a foundational theoretical framework. Extensive empirical studies validate the reliability of the sampling methods presented.

The two leading solution paradigms for imitation learning (IL), BC and GAIL, each suffers from notable drawbacks. BC, a supervised learning approach to mimic expert actions, is vulnerable to covariate shift. GAIL applies adversarial training to minimize the discrepancy between expert and learner behaviors, which is prone to unstable training and mode collapse. In this work, we propose DC – Distributional Cloning – a novel IL approach for addressing the covariate shift and mode collapse problems simultaneously. DC directly maximizes the likelihood of observed expert and learner demonstrations, and gradually encourages the learner to evolve towards expert behaviors based on an averaging effect. The DC solution framework contains two stages in each training loop, where in stage one the mixed expert and learner state distribution is estimated via SoftFlow, and in stage two the learner policy is trained to match both the expert’s policy and state distribution via ADMM. Experimental evaluation of DC compared with several baselines in 10 different physics-based control tasks reveal superior results in learner policy performance, training stability, and mode distribution preservation.

Given historical traffic distributions and associated urban conditions observed in a city, the conditional urban traffic estimation problem aims at estimating realistic future projections of the traffic under a set of new urban conditions, e.g., new bus routes, rainfall intensity and travel demands. The problem is important in reducing traffic congestion, improving public transportation efficiency, and facilitating urban planning. However, solving this problem is challenging due to the strong spatial dependencies of traffic patterns and the complex relations between the traffic and urban conditions. In this paper, we tackle the challenges by proposing a novel Complex-Condition-Controlled Urban Traffic Estimation through Generative Adversarial Networks (C3-GAN) for urban traffic estimation of a region under various complex conditions. C3-GAN features the following three novel designs on top of standard cGAN model: (1) an embedding network mapping the complex conditions to a latent space to find representations of the urban conditions; (2) an inference network to enhance the relations between the embedded latent vectors and the traffic data. Extensive experiments on real-world datasets demonstrate that our C3-GAN produces high-quality traffic estimations and outperforms state-of-the-art baseline methods.

Existing topic modeling and text segmentation methodologies generally require large datasets for training, limiting their capabilities when only small collections of text are available. In this work, we reexamine the inter-related problems of “topic identification” and “text segmentation” for sparse document learning, when there is a single new text of interest. In developing a methodology to handle single documents, we face two major challenges. First is sparse information : with access to only one document, we cannot train traditional topic models or deep learning algorithms. Second is significant noise : a considerable portion of words in any single document will produce only noise and not help discern topics or segments. To tackle these issues, we design an unsupervised, computationally efficient methodology called Biclustering Approach to Topic modeling and Segmentation (BATS). BATS leverages three key ideas to simultaneously identify topics and segment text: (i) a new mechanism that uses word order information to reduce sample complexity, (ii) a statistically sound graph-based biclustering technique that identifies latent structures of words and sentences, and (iii) a collection of effective heuristics that remove noise words and award important words to further improve performance. Experiments on six datasets show that our approach outperforms several state-of-the-art baselines when considering topic coherence, topic diversity, segmentation, and runtime comparison metrics.

Learning to make optimal decisions is a common yet complicated task. While computer agents can learn to make decisions by running reinforcement learning (RL), it remains unclear how human beings learn. In this paper, we perform the first data-driven case study on taxi drivers to validate whether humans mimic RL to learn. We categorize drivers into three groups based on their performance trends and analyze the correlations between human drivers and agents trained using RL. We discover that drivers that become more efficient at earning over time exhibit similar learning patterns to those of agents, whereas drivers that become less efficient tend to do the opposite. Our study (1) provides evidence that some human drivers do adapt RL when learning, (2) enhances the deep understanding of taxi drivers' learning strategies, (3) offers a guideline for taxi drivers to improve their earnings, and (4) develops a generic analytical framework to study and validate human learning strategies.

Many real-world human behaviors can be modeled and characterized as sequential decision-making processes, such as a taxi driver’s choices of working regions and times. Each driver possesses unique preferences on the sequential choices over time and improves the driver’s working efficiency. Understanding the dynamics of such preferences helps accelerate the learning process of taxi drivers. Prior works on taxi operation management mostly focus on finding optimal driving strategies or routes, lacking in-depth analysis on what the drivers learned during the process and how they affect the performance of the driver. In this work, we make the first attempt to establish Dynamic Human Preference Analytics. We inversely learn the taxi drivers’ preferences from data and characterize the dynamics of such preferences over time. We extract two types of features (i.e., profile features and habit features) to model the decision space of drivers. Then through inverse reinforcement learning, we learn the preferences of drivers with respect to these features. The results illustrate that self-improving drivers tend to keep adjusting their preferences to habit features to increase their earning efficiency while keeping the preferences to profile features invariant. However, experienced drivers have stable preferences over time. The exploring drivers tend to randomly adjust the preferences over time.

Many real world human behaviors can be modeled and characterized as sequential decision making processes, such as taxi driver's choices of working regions and times. Each driver possesses unique preferences on the sequential choices over time and improves their working efficiency. Understanding the dynamics of such preferences helps accelerate the learning process of taxi drivers. Prior works on taxi operation management mostly focus on finding optimal driving strategies or routes, lacking in-depth analysis on what the drivers learned during the process and how they affect the performance of the driver. In this work, we make the first attempt to inversely learn the taxi drivers' preferences from data and characterize the dynamics of such preferences over time. We extract two types of features, i.e., profile features and habit features, to model the decision space of drivers. Then through inverse reinforcement learning we learn the preferences of drivers with respect to these features. The results illustrate that self-improving drivers tend to keep adjusting their preferences to habit features to increase their earning efficiency, while keeping the preferences to profile features invariant. On the other hand, experienced drivers have stable preferences over time.

We revisit the problem of predicting directional movements of stock prices based on news articles: here our algorithm uses daily articles from The Wall Street Journal to predict the closing stock prices on the same day. We propose a unified latent space model to characterize the "co-movements" between stock prices and news articles. Unlike many existing approaches, our new model is able to simultaneously leverage the correlations: (a) among stock prices, (b) among news articles, and (c) between stock prices and news articles. Thus, our model is able to make daily predictions on more than 500 stocks (most of which are not even mentioned in any news article) while having low complexity. We carry out extensive back testing on trading strategies based on our algorithm. The result shows that our model has substantially better accuracy rate (55.7%) compared to many widely used algorithms. The return (56%) and Sharpe ratio due to a trading strategy based on our model are also much higher than baseline indices.

We consider the continual count tracking problem in a distributed environment where the input is an aggregate stream that originates from k distinct sites and the updates are allowed to be non-monotonic, i.e. both increments and decrements are allowed. The goal is to continually track the count within a prescribed relative accuracy ε at the lowest possible communication cost. Specifically, we consider an adversarial setting where the input values are selected and assigned to sites by an adversary but the order is according to a random permutation or is a random i.i.d process. The input stream of values is allowed to be non-monotonic with an unknown drift -1≤μ=1 where the case μ = 1 corresponds to the special case of a monotonic stream of only non-negative updates. We show that a randomized algorithm guarantees to track the count accurately with high probability and has the expected communication cost Õ(min√k/(|#956;|ε), √k n/ε, n}), for an input stream of length n, and establish matching lower bounds. This improves upon previously best known algorithm whose expected communication cost is Θ(min√k/ε,n]) that applies only to an important but more restrictive class of monotonic input streams, and our results are substantially more positive than the communication complexity of Ω(n) under fully adversarial input. We also show how our framework can also accommodate other types of random input streams, including fractional Brownian motion that has been widely used to model temporal long-range dependencies observed in many natural phenomena. Last but not least, we show how our non-monotonic counter can be applied to track the second frequency moment and to a Bayesian linear regression problem.

Influence maximization, defined by Kempe, Kleinberg, and Tardos (2003), is the problem of finding a small set of seed nodes in a social network that maximizes the spread of influence under certain influence cascade models. In this paper, we propose an extension to the independent cascade model that incorporates the emergence and propagation of negative opinions. The new model has an explicit parameter called quality factor to model the natural behavior of people turning negative to a product due to product defects. Our model incorporates negativity bias (negative opinions usually dominate over positive opinions) commonly acknowledged in the social psychology literature. The model maintains some nice properties such as submodularity, which allows a greedy approximation algorithm for maximizing positive influence within a ratio of 1 – 1/e. We define a quality sensitivity ratio (qs-ratio) of influence graphs and show a tight bound of on the qs-ratio, where n is the number of nodes in the network and k is the number of seeds selected, which indicates that seed selection is sensitive to the quality factor for general graphs. We design an efficient algorithm to compute influence in tree structures, which is nontrivial due to the negativity bias in the model. We use this algorithm as the core to build a heuristic algorithm for influence maximization for general graphs. Through simulations, we show that our heuristic algorithm has matching influence with a standard greedy approximation algorithm while being orders of magnitude faster.