arXiv subjects

Quan Yuan

Publications and source records attributed to Quan Yuan.

52 records · Page 3Linked to original sources

arXiv2023

BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information

Automated reasoning with unstructured natural text is a key requirement for many potential applications of NLP and for developing robust AI systems. Recently, Language Models (LMs) have demonstrated complex reasoning capacities even without any finetuning. However, existing evaluation for automated reasoning assumes access to a consistent and coherent set of information over which models reason. When reasoning in the real-world, the available information is frequently inconsistent or contradictory, and therefore models need to be equipped with a strategy to resolve such conflicts when they arise. One widely-applicable way of resolving conflicts is to impose preferences over information sources (e.g., based on source credibility or information recency) and adopt the source with higher preference. In this paper, we formulate the problem of reasoning with contradictory information guided by preferences over sources as the classical problem of defeasible reasoning, and develop a dataset called BoardgameQA for measuring the reasoning capacity of LMs in this setting. BoardgameQA also incorporates reasoning with implicit background knowledge, to better reflect reasoning problems in downstream applications. We benchmark various LMs on BoardgameQA and the results reveal a significant gap in the reasoning capacity of state-of-the-art LMs on this problem, showing that reasoning with conflicting information does not surface out-of-the-box in LMs. While performance can be improved with finetuning, it nevertheless remains poor.

cs.CL↗

arXiv2023

Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play

Standard empirical risk minimization (ERM) training can produce deep neural network (DNN) models that are accurate on average but under-perform in under-represented population subgroups, especially when there are imbalanced group distributions in the long-tailed training data. Therefore, approaches that improve the accuracy-group robustness trade-off frontier of a DNN model (i.e. improving worst-group accuracy without sacrificing average accuracy, or vice versa) is of crucial importance. Uncertainty-based active learning (AL) can potentially improve the frontier by preferentially sampling underrepresented subgroups to create a more balanced training dataset. However, the quality of uncertainty estimates from modern DNNs tend to degrade in the presence of spurious correlations and dataset bias, compromising the effectiveness of AL for sampling tail groups. In this work, we propose Introspective Self-play (ISP), a simple approach to improve the uncertainty estimation of a deep neural network under dataset bias, by adding an auxiliary introspection task requiring a model to predict the bias for each data point in addition to the label. We show that ISP provably improves the bias-awareness of the model representation and the resulting uncertainty estimates. On two real-world tabular and language tasks, ISP serves as a simple "plug-in" for AL model training, consistently improving both the tail-group sampling rate and the final accuracy-fairness trade-off frontier of popular AL methods.

cs.LG↗

arXiv2023

Panacea or Placebo? Exploring Causal Effects of Nonlocal Vehicle Driving Restriction Policies on Traffic Congestion Using Difference-in-differences Approach

Car dependence has been threatening transportation sustainability as it contributes to congestion and associated externalities. In response, various transport policies that restrict the use of private vehicle have been implemented. However, empirical evaluations of such policies have been limited. To assess these policies' benefits and costs, it is imperative to accurately evaluate how such policies affect traffic conditions. In this study, we compile a refined spatio-temporal resolution data set of the floating-vehicle-based traffic performance index to examine the effects of a recent nonlocal vehicle driving restriction policy in Shanghai, one of most populous cities in the world. Specifically, we explore whether and how the policy impacted traffic speeds in the short term by employing a quasi-experimental difference-in-differences modeling approach. We find that: (1) In the first month, the policy led to an increase of the network-level traffic speed by 1.47% (0.352 km/h) during evening peak hours (17:00-19:00) but had no significant effects during morning peak hours (7:00-9:00). (2) The policy also helped improve the network-level traffic speed in some unrestricted hours (6:00, 12:00, 14:00, and 20:00) although the impact was marginal. (3) The short-term effects of the policy exhibited heterogeneity across traffic analysis zones. The lower the metro station density, the greater the effects were. We conclude that driving restrictions for non-local vehicles alone may not significantly reduce congestion, and their effects can differ both temporally and spatially. However, they can have potential side effects such as increased purchase and usage of new energy vehicles, owners of which can obtain a local license plate of Shanghai for free.

econ.GN↗

arXiv2021

Artificial Intelligence Powered Mobile Networks: From Cognition to Decision

Mobile networks (MN) are anticipated to provide unprecedented opportunities to enable a new world of connected experiences and radically shift the way people interact with everything. MN are becoming more and more complex, driven by ever-increasingly complicated configuration issues and blossoming new service requirements. This complexity poses significant challenges in deployment, management, operation, optimization, and maintenance, since they require a complete understanding and cognition of MN. Artificial intelligence (AI), which deals with the simulation of intelligent behavior in computers, has demonstrated enormous success in many application domains, suggesting its potential in cognizing the state of MN and making intelligent decisions. In this paper, we first propose an AI-powered mobile network architecture and discuss challenges in terms of cognition complexity, decisions with high-dimensional action space, and self-adaption to system dynamics. Then, potential solutions that are associated with AI are discussed. Finally, we propose a deep learning approach that directly maps the state of MN to perceived QoS, integrating cognition with the decision. Our proposed approach helps operators in making more intelligent decisions to guarantee QoS. Meanwhile, the effectiveness and advantages of our proposed approach are demonstrated on a real-world dataset, involving $31261$ users over $77$ stations within $5$ days.

cs.NI↗

arXiv2021

SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

AlphaStar, the AI that reaches GrandMaster level in StarCraft II, is a remarkable milestone demonstrating what deep reinforcement learning can achieve in complex Real-Time Strategy (RTS) games. However, the complexities of the game, algorithms and systems, and especially the tremendous amount of computation needed are big obstacles for the community to conduct further research in this direction. We propose a deep reinforcement learning agent, StarCraft Commander (SCC). With order of magnitude less computation, it demonstrates top human performance defeating GrandMaster players in test matches and top professional players in a live event. Moreover, it shows strong robustness to various human strategies and discovers novel strategies unseen from human plays. In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.

cs.LG↗

arXiv2020

Large Scale Product Graph Construction for Recommendation in E-commerce

Building a recommendation system that serves billions of users on daily basis is a challenging problem, as the system needs to make astronomical number of predictions per second based on real-time user behaviors with O(1) time complexity. Such kind of large scale recommendation systems usually rely heavily on pre-built index of products to speedup the recommendation service so that online user waiting time is un-noticeable. One important indexing structure is the product-product index, where one can retrieval a list of ranked products given a seed product. The index can be viewed as a weighted product-product graph. In this paper, we present our novel technologies to efficiently build such kind of indexed product graphs. In particular, we propose the Swing algorithm to capture the substitute relationships between products, which can utilize the substructures of user-item click bi-partitive graph. Then we propose the Surprise algorithm for the modeling of complementary product relationships, which utilizes product category information and solves the sparsity problem of user co-purchasing graph via clustering technique. Base on these two approaches, we can build the basis product graph for recommendation in Taobao. The approaches are evaluated comprehensively with both offline and online experiments, and the results demonstrate the effectiveness and efficiency of the work.

cs.IR↗

arXiv2020

Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts

Nowadays, recommender systems (RSes) are becoming increasingly important to individual users and business marketing, especially in the online e-commerce scenarios. However, while the majority of recommendation algorithms proposed in the literature have focused their efforts on improving prediction accuracy, other important aspects of recommendation quality, such as diversity of recommendations, have been more or less overlooked. In the latest decade, recommendation diversity has drawn more research attention, especially in the models based on user-item bipartite networks. In this paper, we introduce a family of approaches to extract fabricated experts from users in RSes, named as the Expert Tracking Approaches (ExTrA for short), and explore the capability of these fabricated experts in improving the recommendation diversity, by highlighting them in a well-known bipartite network-based method, called the Mass Diffusion (MD for short) model. These ExTrA-based models are compared with two state-of-the-art MD-improved models HHP and BHC, with respect to recommendation accuracy and diversity. Comprehensive empirical results on three real-world datasets MovieLens, Netflix and RYM show that, our proposed ExTrA-based models can achieve significant diversity gain while maintain comparable level of recommendation accuracy.

cs.SI↗

arXiv2020

Alleviating the recommendation bias via rank aggregation

The primary goal of a recommender system is often known as "helping users find relevant items", and a lot of recommendation algorithms are proposed accordingly. However, these accuracy-oriented methods usually suffer the problem of recommendation bias on popular items, which is not welcome to not only users but also item providers. To alleviate the recommendation bias problem, we propose a generic rank aggregation framework for the recommendation results of an existing algorithm, in which the user- and item-oriented ranking results are linearly aggregated together, with a parameter controlling the weight of the latter ranking process. Experiment results of a typical algorithm on two real-world data sets show that, this framework is effective to improve the recommendation fairness of any existing accuracy-oriented algorithms, while avoiding significant accuracy loss.

cs.SI↗

arXiv2020

User Validation of Recommendation Serendipity Metrics

Though it has been recognized that recommending serendipitous (i.e., surprising and relevant) items can be helpful for increasing users' satisfaction and behavioral intention, how to measure serendipity in the offline environment is still an open issue. In recent years, a number of metrics have been proposed, but most of them were based on researchers' assumptions due to the serendipity's subjective nature. In order to validate these metrics' actual performance, we collected over 10,000 users' real feedback data and compared with the metrics' results. It turns out the user profile based metrics, especially content-based ones, perform better than those based on item popularity, in terms of estimating the unexpectedness facet of recommendations. Moreover, the full metrics, which involve the unexpectedness component, relevance, timeliness, and user curiosity, can more accurately indicate the recommendation's serendipity degree, relative to those that just involve some of them. The application of these metrics to several recommender algorithms further consolidates their practical usage, because the comparison results are consistent with those from user evaluation. Thus, this work is constructive for filling the gap between offline measurement and user study on recommendation serendipity.

cs.HC↗

arXiv2019

Phase noise accumulation in recirculating frequency shifting loop based programmable optical frequency comb

The phenomenon of linewidth continuously broadening along with the recirculation number in recirculating frequency shifting loop is observed. In this paper, a novel method of measuring the phase noise accumulation induced by EDFA in recirculating frequency shifting loop is proposed and the experiment results support the viewpoint of the laser linewidth will be broadening by EDFA. An empirical formula has been extracted to estimate the linewidth deterioration of the RFS output. We demonstrate the relationship between the linewidth and the recirculation number of the RFS based optical frequency comb in both theoretically and experimentally. By employing the recirculation frequency shifting loop, the phase noise accumulation induced by EDFA could be measured obviously and the linewidth of each tone can be measured precisely.

physics.optics↗

arXiv2019

Artificial Intelligence for Prosthetics - challenge solutions

In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants were invited to describe their algorithms. In this work, we describe the challenge and present thirteen solutions that used deep reinforcement learning approaches. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each team implemented different modifications of the known algorithms by, for example, dividing the task into subtasks, learning low-level control, or by incorporating expert knowledge and using imitation learning.

cs.LG↗

arXiv2019

Blind Motion Deblurring with Cycle Generative Adversarial Networks

Blind motion deblurring is one of the most basic and challenging problems in image processing and computer vision. It aims to recover a sharp image from its blurred version knowing nothing about the blur process. Many existing methods use Maximum A Posteriori (MAP) or Expectation Maximization (EM) frameworks to deal with this kind of problems, but they cannot handle well the figh frequency features of natural images. Most recently, deep neural networks have been emerging as a powerful tool for image deblurring. In this paper, we prove that encoder-decoder architecture gives better results for image deblurring tasks. In addition, we propose a novel end-to-end learning model which refines generative adversarial network by many novel training strategies so as to tackle the problem of deblurring. Experimental results show that our model can capture high frequency features well, and the results on benchmark dataset show that proposed model achieves the competitive performance.

cs.CV↗

arXiv2017

Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games

Many artificial intelligence (AI) applications often require multiple intelligent agents to work in a collaborative effort. Efficient learning for intra-agent communication and coordination is an indispensable step towards general AI. In this paper, we take StarCraft combat game as a case study, where the task is to coordinate multiple agents as a team to defeat their enemies. To maintain a scalable yet effective communication protocol, we introduce a Multiagent Bidirectionally-Coordinated Network (BiCNet ['bIknet]) with a vectorised extension of actor-critic formulation. We show that BiCNet can handle different types of combats with arbitrary numbers of AI agents for both sides. Our analysis demonstrates that without any supervisions such as human demonstrations or labelled data, BiCNet could learn various types of advanced coordination strategies that have been commonly used by experienced game players. In our experiments, we evaluate our approach against multiple baselines under different scenarios; it shows state-of-the-art performance, and possesses potential values for large-scale real-world applications.

cs.AI↗

arXiv2015

A Weight-coded Evolutionary Algorithm for the Multidimensional Knapsack Problem

A revised weight-coded evolutionary algorithm (RWCEA) is proposed for solving multidimensional knapsack problems. This RWCEA uses a new decoding method and incorporates a heuristic method in initialization. Computational results show that the RWCEA performs better than a weight-coded evolutionary algorithm proposed by Raidl (1999) and to some existing benchmarks, it can yield better results than the ones reported in the OR-library.

cs.NE↗

arXiv2014

Analyzing Convergence and Rates of Convergence of Particle Swarm Optimization Algorithms Using Stochastic Approximation Methods

Recently, much progress has been made on particle swarm optimization (PSO). A number of works have been devoted to analyzing the convergence of the underlying algorithms. Nevertheless, in most cases, rather simplified hypotheses are used. For example, it often assumes that the swarm has only one particle. In addition, more often than not, the variables and the points of attraction are assumed to remain constant throughout the optimization process. In reality, such assumptions are often violated. Moreover, there are no rigorous rates of convergence results available to date for the particle swarm, to the best of our knowledge. In this paper, we consider a general form of PSO algorithms, and analyze asymptotic properties of the algorithms using stochastic approximation methods. We introduce four coefficients and rewrite the PSO procedure as a stochastic approximation type iterative algorithm. Then we analyze its convergence using weak convergence method. It is proved that a suitably scaled sequence of swarms converge to the solution of an ordinary differential equation. We also establish certain stability results. Moreover, convergence rates are ascertained by using weak convergence method. A centered and scaled sequence of the estimation errors is shown to have a diffusion limit.

math.OC↗

arXiv2013

On the performance of a hybrid genetic algorithm in dynamic environments

The ability to track the optimum of dynamic environments is important in many practical applications. In this paper, the capability of a hybrid genetic algorithm (HGA) to track the optimum in some dynamic environments is investigated for different functional dimensions, update frequencies, and displacement strengths in different types of dynamic environments. Experimental results are reported by using the HGA and some other existing evolutionary algorithms in the literature. The results show that the HGA has better capability to track the dynamic optimum than some other existing algorithms.

cs.NE↗