Xin Bai

Xin Bai

Auto-generated profile, based on publicly available information

Xin Bai

Huawei Technologies Co. Ltd China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 July 2021 in IEEE Access
Verified
Journal Article
Open access
SBSen Bai
Sen Bai
XBXin Bai
Xin Bai
Traffic congestion has long been a worldwide difficult problem in metropolitan transportation networks, incurring tremendous time waste and exhaust pollution. Extensive efforts have been made to address this problem, among which traffic control at intersections is known to be especially crucial while challenging. Also, it is helpful to the recent advent of autopilot technologies by enhancing the schedule accuracy and reducing the infrastructure cost. In practice, however, existing researches can hardly work well in a pervasive manner since they are essentially limited to two ideal assumptions: 1) each intersection comprises four ways; 2) each way is homogeneously composed of two lanes. Through an in-depth examination of their basic models, we find that the two-fold ideal assumptions are largely compelled by the surprisingly high complexity of converting a practical intersection topology into a theoretical conflict graph. Moreover, existing works seldom consider the modeling of complex intersections in the scene of cooperative control of multiply intersections. Driven by the above understandings, our first effort towards a general framework (for handling multiple-way heterogeneous intersections) is to carefully transform a practical intersection topology into a homomorphic, regular conflict graph which is suited to theoretical modeling and further processing with an affordable complexity. Besides, a maximum weight independent set (MWIS) based approach is proposed to minimize the average waiting time of vehicles at an isolated intersection. In addition, we apply a backpressure-based algorithm to our framework to further optimize the global average waiting time of vehicles in a whole road network. Simulation results have demonstrated that the average waiting time achieved by our approach is merely 80 seconds while traditional traffic light control reaches 370 seconds.

15 December 2022 in IEEE Transactions on Mobile Computing
Verified
Journal Article
Closed access
SBSen Bai
Sen Bai
STShoufeng Tong
Shoufeng Tong
林吉林省明虹科技有限公司 吉
林省明虹科技有限公司 吉
JZJiang zhengang
Jiang zhengang
XBXin Bai
Xin Bai
RXRanqi Xu
Ranqi Xu
The booming crowdsourced delivery leverages networks of local, part time couriers to meet growing customer demands for increasingly speedy shipping. By conducting city-wide low-cost delivery networks, crowd-sourced enabled instant delivery platforms have fought to figure out a way to offer instant shipping at low price. Nevertheless, limited ubiquitous computing infrastructures impede the discovery of equilibrium between cost reduction and sufficient shipping capacity. In this article, we present our endeavor towards understanding and designing a dynamic pricing framework based on a large-scale food-delivery platform. To reduce delivery fees in capacity overload regions and resolve the decline of service quality caused by insufficient shipping capacity, we address the challenge of quantifying the inter-regional shipping capacity disparities by accordingly applying a variety of techniques, including cooperative game theory, probability analysis and address entity recognition. In particular, we provide an $O(n^{2})$ algorithm for the cooperative game based cost allocation, of which the exponential computational complexity $O(n^{2}2^{n})$ is generally considered a major challenge in real-world applications. City-wide experiments in Nanjing and Shenzhen illustrate that we achieve a 10% decrease in delivery fees under overload shipping capacity and a 3% increase in completion rates in customer locations with poor service quality.

1 February 2019 in Computer Networks
Verified
Journal Article
Closed access
SBSen Bai
Sen Bai
YLYunhao Liu
Yunhao Liu
Zhenhua LiZhenhua Li
Zhenhua Li
XBXin Bai
Xin Bai

27 May 2025 in arXiv
Verified
Preprint
Open access
PDF file
SBSen Bai
Sen Bai
CYChunqi Yang
Chunqi Yang
XBXin Bai
Xin Bai
XZXin Zhang
Xin Zhang
JZJiang zhengang
Jiang zhengang
Binary (0-1) integer programming (BIP) is pivotal in scientific domains requiring discrete decision-making. As the advance of AI computing, recent works explore neural network-based solvers for integer linear programming (ILP) problems. Yet, they lack scalability for tackling nonlinear challenges. To handle nonlinearities, state-of-the-art Branch-and-Cut solvers employ linear relaxations, leading to exponential growth in auxiliary variables and severe computation limitations. To overcome these limitations, we propose BIPNN (Binary Integer Programming Neural Network), an unsupervised learning framework to solve nonlinear BIP problems via hypergraph neural networks (HyperGNN). Specifically, BIPNN reformulates BIPs-constrained, discrete, and nonlinear (sin, log, exp) optimization problems-into unconstrained, differentiable, and polynomial loss functions. The reformulation stems from the observation of a precise one-to-one mapping between polynomial BIP objectives and hypergraph structures, enabling the unsupervised training of HyperGNN to optimize BIP problems in an end-to-end manner. On this basis, we propose a GPU-accelerated and continuous-annealing-enhanced training pipeline for BIPNN. The pipeline enables BIPNN to optimize large-scale nonlinear terms in BIPs fully in parallel via straightforward gradient descent, thus significantly reducing the training cost while ensuring the generation of discrete, high-quality solutions. Extensive experiments on synthetic and real-world datasets highlight the superiority of our approach.

27 May 2025 in arXiv
Verified
Preprint
Open access
PDF file
SBSen Bai
Sen Bai
CYChunqi Yang
Chunqi Yang
XBXin Bai
Xin Bai
XZXin Zhang
Xin Zhang
JZJiang zhengang
Jiang zhengang
Along with AI computing shining in scientific discovery, its potential in the combinatorial optimization (CO) domain has also emerged in recent years. Yet, existing unsupervised neural network solvers struggle to solve $k$-grouping problems (e.g., coloring, partitioning) on large-scale graphs and hypergraphs, due to limited computational frameworks. In this work, we propose Deep $k$-grouping, an unsupervised learning-based CO framework. Specifically, we contribute: Novel one-hot encoded polynomial unconstrained binary optimization (OH-PUBO), a formulation for modeling k-grouping problems on graphs and hypergraphs (e.g., graph/hypergraph coloring and partitioning); GPU-accelerated algorithms for large-scale k-grouping CO problems. Deep $k$-grouping employs the relaxation of large-scale OH-PUBO objectives as differentiable loss functions and trains to optimize them in an unsupervised manner. To ensure scalability, it leverages GPU-accelerated algorithms to unify the training pipeline; A Gini coefficient-based continuous relaxation annealing strategy to enforce discreteness of solutions while preventing convergence to local optima. Experimental results demonstrate that Deep $k$-grouping outperforms existing neural network solvers and classical heuristics such as SCIP and Tabu.