262 citations · 929 across the 43 of their papers we have counts for
44 papers
Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal
Zhentao Tan, Yue Wu, Qiankun Liu +4
Image restoration under adverse weather conditions (e.g., rain, snow and haze) is a fundamental computer vision problem and has important indications for various downstream applica…
Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems
Xiong-Hui Chen, Bowei He, Yang Yu +5
Long-term user engagement (LTE) optimization in sequential recommender systems (SRS) is shown to be suited by reinforcement learning (RL) which finds a policy to maximize long-term…
Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module
Linzhi Huang, Yulong Li, Hongbo Tian +4
In this paper, we delve into semi-supervised 2D human pose estimation. The previous method ignored two problems: (i) When conducting interactive training between large model and li…
Towards Capacity-Aware Broker Matching: From Recommendation to Assignment
Shuyue Wei, Yongxin Tong, Zimu Zhou +4
Online real estate platforms are gaining increasing popularity, where a central issue is to match brokers with clients for potential housing transactions. Mainstream platforms matc…
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
Shuang Qiu, Xiaohan Wei, Jieping Ye +2
While single-agent policy optimization in a fixed environment has attracted a lot of research attention recently in the reinforcement learning community, much less is known theoret…
Rethinking Graph Convolutional Networks in Knowledge Graph Completion
Zhanqiu Zhang, Jie Wang, Jieping Ye +1
Graph convolutional networks (GCNs) -- which are effective in modeling graph structures -- have been increasingly popular in knowledge graph completion (KGC). GCN-based KGC models…
On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game
Shuang Qiu, Jieping Ye, Zhaoran Wang +1
To achieve sample efficiency in reinforcement learning (RL), it necessitates efficiently exploring the underlying environment. Under the offline setting, addressing the exploration…
Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms
Xiaocheng Tang, Fan Zhang, Zhiwei Qin +6
Large ride-hailing platforms, such as DiDi, Uber and Lyft, connect tens of thousands of vehicles in a city to millions of ride demands throughout the day, providing great promises…
Reinforcement Learning for Ridesharing: An Extended Survey
Zhiwei Qin, Hongtu Zhu, Jieping Ye
In this paper, we present a comprehensive, in-depth survey of the literature on reinforcement learning approaches to decision optimization problems in a typical ridesharing system.…
Graph-Based Equilibrium Metrics for Dynamic Supply-Demand Systems with Applications to Ride-sourcing Platforms
Fan Zhou, Shikai Luo, Xiaohu Qie +2
How to dynamically measure the local-to-global spatio-temporal coherence between demand and supply networks is a fundamental task for ride-sourcing platforms, such as DiDi. Such co…
Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning
Yan Jiao, Xiaocheng Tang, Zhiwei Qin +4
We present a new practical framework based on deep reinforcement learning and decision-time planning for real-world vehicle repositioning on ride-hailing (a type of mobility-on-dem…
Successive Projection for Solving Systems of Nonlinear Equations/Inequalities
Wen-Jun Zeng, Jieping Ye
Solving large-scale systems of nonlinear equations/inequalities is a fundamental problem in computing and optimization. In this paper, we propose a generic successive projection (S…
Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
Bingyu Liu, Yuhong Guo, Jieping Ye +1
Recent domain adaptation methods have demonstrated impressive improvement on unsupervised domain adaptation problems. However, in the semi-supervised domain adaptation (SSDA) setti…
Domain Adaptation with Incomplete Target Domains
Zhenpeng Li, Jianan Jiang, Yuhong Guo +3
Domain adaptation, as a task of reducing the annotation cost in a target domain by exploiting the existing labeled data in an auxiliary source domain, has received a lot of attenti…
Bi-Dimensional Feature Alignment for Cross-Domain Object Detection
Zhen Zhao, Yuhong Guo, Jieping Ye
Recently the problem of cross-domain object detection has started drawing attention in the computer vision community. In this paper, we propose a novel unsupervised cross-domain de…
Joint predictions of multi-modal ride-hailing demands: a deep multi-task multigraph learning-based approach
Jintao Ke, Siyuan Feng, Zheng Zhu +2
Ride-hailing platforms generally provide various service options to customers, such as solo ride services, shared ride services, etc. It is generally expected that demands for diff…
Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction
Xuanzhao Wang, Zhengping Che, Bo Jiang +6
Video anomaly detection is commonly used in many applications such as security surveillance and is very challenging.A majority of recent video anomaly detection approaches utilize…
DiDi's Machine Translation System for WMT2020
Tanfang Chen, Weiwei Wang, Wenyang Wei +4
This paper describes DiDi AI Labs' submission to the WMT2020 news translation shared task. We participate in the translation direction of Chinese->English. In this direction, we us…
Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control
Zhiyuan Xu, Kun Wu, Zhengping Che +2
While Deep Reinforcement Learning (DRL) has emerged as a promising approach to many complex tasks, it remains challenging to train a single DRL agent that is capable of undertaking…
Meta Graph Attention on Heterogeneous Graph with Node-Edge Co-evolution
Yucheng Lin, Huiting Hong, Xiaoqing Yang +3
Graph neural networks have become an important tool for modeling structured data. In many real-world systems, intricate hidden information may exist, e.g., heterogeneity in nodes/e…
Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning
Shuang Qiu, Zhuoran Yang, Xiaohan Wei +2
Temporal-Difference (TD) learning with nonlinear smooth function approximation for policy evaluation has achieved great success in modern reinforcement learning. It is shown that s…
Predicting Individual Treatment Effects of Large-scale Team Competitions in a Ride-sharing Economy
Teng Ye, Wei Ai, Lingyu Zhang +4
Millions of drivers worldwide have enjoyed financial benefits and work schedule flexibility through a ride-sharing economy, but meanwhile they have suffered from the lack of a sens…
PropagationNet: Propagate Points to Curve to Learn Structure Information
Xiehe Huang, Weihong Deng, Haifeng Shen +2
Deep learning technique has dramatically boosted the performance of face alignment algorithms. However, due to large variability and lack of samples, the alignment problem in uncon…
Road Network Metric Learning for Estimated Time of Arrival
Yiwen Sun, Kun Fu, Zheng Wang +2
Recently, deep learning have achieved promising results in Estimated Time of Arrival (ETA), which is considered as predicting the travel time from the origin to the destination alo…