Jie Wang

Mingxuan Ye, Yufei Kuang, Jie Wang et al.

While deep reinforcement learning (RL) has been demonstrated effective in solving complex control tasks, sample efficiency remains a key challenge due to the large amounts of data required for remarkable performance. Existing research explores the application of representation learning for data-efficient RL, e.g., learning predictive representations by predicting long-term future states. However, many existing methods do not fully exploit the structural information inherent in sequential state signals, which can potentially improve the quality of long-term decision-making but is difficult to discern in the time domain. To tackle this problem, we propose State Sequences Prediction via Fourier Transform (SPF), a novel method that exploits the frequency domain of state sequences to extract the underlying patterns in time series data for learning expressive representations efficiently. Specifically, we theoretically analyze the existence of structural information in state sequences, which is closely related to policy performance and signal regularity, and then propose to predict the Fourier transform of infinite-step future state sequences to extract such information. One of the appealing features of SPF is that it is simple to implement while not requiring storage of infinite-step future states as prediction targets. Experiments demonstrate that the proposed method outperforms several state-of-the-art algorithms in terms of both sample efficiency and performance.

Yufei Kuang, Xijun Li, Jie Wang et al.

Large-scale LP problems from industry usually contain much redundancy that severely hurts the efficiency and reliability of solving LPs, making presolve (i.e., the problem simplification module) one of the most critical components in modern LP solvers. However, how to design high-quality presolve routines -- that is, the program determining (P1) which presolvers to select, (P2) in what order to execute, and (P3) when to stop -- remains a highly challenging task due to the extensive requirements on expert knowledge and the large search space. Due to the sequential decision property of the task and the lack of expert demonstrations, we propose a simple and efficient reinforcement learning (RL) framework -- namely, reinforcement learning for presolve (RL4Presolve) -- to tackle (P1)-(P3) simultaneously. Specifically, we formulate the routine design task as a Markov decision process and propose an RL framework with adaptive action sequences to generate high-quality presolve routines efficiently. Note that adaptive action sequences help learn complex behaviors efficiently and adapt to various benchmarks. Experiments on two solvers (open-source and commercial) and eight benchmarks (real-world and synthetic) demonstrate that RL4Presolve significantly and consistently improves the efficiency of solving large-scale LPs, especially on benchmarks from industry. Furthermore, we optimize the hard-coded presolve routines in LP solvers by extracting rules from learned policies for simple and efficient deployment to Huawei's supply chain. The results show encouraging economic and academic potential for incorporating machine learning to modern solvers.

Minyi Zhao, Yi Xu, Bingjia Li et al.

Scene text image super-resolution (STISR) is an important pre-processing technique for text recognition from low-resolution scene images. Nowadays, various methods have been proposed to extract text-specific information from high-resolution (HR) images to supervise STISR model training. However, due to uncontrollable factors (e.g. shooting equipment, focus, and environment) in manually photographing HR images, the quality of HR images cannot be guaranteed, which unavoidably impacts STISR performance. Observing the quality issue of HR images, in this paper we propose a novel idea to boost STISR by first enhancing the quality of HR images and then using the enhanced HR images as supervision to do STISR. Concretely, we develop a new STISR framework, called High-Resolution ENhancement (HiREN) that consists of two branches and a quality estimation module. The first branch is developed to recover the low-resolution (LR) images, and the other is an HR quality enhancement branch aiming at generating high-quality (HQ) text images based on the HR images to provide more accurate supervision to the LR images. As the degradation from HQ to HR may be diverse, and there is no pixel-level supervision for HQ image generation, we design a kernel-guided enhancement network to handle various degradation, and exploit the feedback from a recognizer and text-level annotations as weak supervision signal to train the HR enhancement branch. Then, a quality estimation module is employed to evaluate the qualities of HQ images, which are used to suppress the erroneous supervision information by weighting the loss of each image. Extensive experiments on TextZoom show that HiREN can work well with most existing STISR methods and significantly boost their performances.

Zijie Geng, Xijun Li, Jie Wang et al.

In the past few years, there has been an explosive surge in the use of machine learning (ML) techniques to address combinatorial optimization (CO) problems, especially mixed-integer linear programs (MILPs). Despite the achievements, the limited availability of real-world instances often leads to sub-optimal decisions and biased solver assessments, which motivates a suite of synthetic MILP instance generation techniques. However, existing methods either rely heavily on expert-designed formulations or struggle to capture the rich features of real-world instances. To tackle this problem, we propose G2MILP, the first deep generative framework for MILP instances. Specifically, G2MILP represents MILP instances as bipartite graphs, and applies a masked variational autoencoder to iteratively corrupt and replace parts of the original graphs to generate new ones. The appealing feature of G2MILP is that it can learn to generate novel and realistic MILP instances without prior expert-designed formulations, while preserving the structures and computational hardness of real-world datasets, simultaneously. Thus the generated instances can facilitate downstream tasks for enhancing MILP solvers under limited data availability. We design a suite of benchmarks to evaluate the quality of the generated MILP instances. Experiments demonstrate that our method can produce instances that closely resemble real-world datasets in terms of both structures and computational hardness. The deliverables are released at https://miralab-ustc.github.io/L2O-G2MILP.

Haoyang Liu, Yufei Kuang, Jie Wang et al.

Machine learning has been successfully applied to improve the efficiency of Mixed-Integer Linear Programming (MILP) solvers. However, the learning-based solvers often suffer from severe performance degradation on unseen MILP instances -- especially on large-scale instances from a perturbed environment -- due to the limited diversity of training distributions. To tackle this problem, we propose a novel approach, which is called Adversarial Instance Augmentation and does not require to know the problem type for new instance generation, to promote data diversity for learning-based branching modules in the branch-and-bound (B&B) Solvers (AdaSolver). We use the bipartite graph representations for MILP instances and obtain various perturbed instances to regularize the solver by augmenting the graph structures with a learned augmentation policy. The major technical contribution of AdaSolver is that we formulate the non-differentiable instance augmentation as a contextual bandit problem and adversarially train the learning-based solver and augmentation policy, enabling efficient gradient-based training of the augmentation policy. To the best of our knowledge, AdaSolver is the first general and effective framework for understanding and improving the generalization of both imitation-learning-based (IL-based) and reinforcement-learning-based (RL-based) B&B solvers. Extensive experiments demonstrate that by producing various augmented instances, AdaSolver leads to a remarkable efficiency improvement across various distributions.

Zixuan Li, Haiying Lin, Zhangyu Wang et al.

Ground segmentation, as the basic task of unmanned intelligent perception, provides an important support for the target detection task. Unstructured road scenes represented by open-pit mines have irregular boundary lines and uneven road surfaces, which lead to segmentation errors in current ground segmentation methods. To solve this problem, a ground segmentation method based on point cloud map is proposed, which involves three parts: region of interest extraction, point cloud registration and background subtraction. Firstly, establishing boundary semantic associations to obtain regions of interest in unstructured roads. Secondly, establishing the location association between point cloud map and the real-time point cloud of region of interest by semantics information. Thirdly, establishing a background model based on Gaussian distribution according to location association, and segments the ground in real-time point cloud by the background substraction method. Experimental results show that the correct segmentation rate of ground points is 99.95%, and the running time is 26ms. Compared with state of the art ground segmentation algorithm Patchwork++, the average accuracy of ground point segmentation is increased by 7.43%, and the running time is increased by 17ms. Furthermore, the proposed method is practically applied to unstructured road scenarios represented by open pit mines.

Long Bai, Guankun Wang, Jie Wang et al.

In the realm of automated robotic surgery and computer-assisted interventions, understanding robotic surgical activities stands paramount. Existing algorithms dedicated to surgical activity recognition predominantly cater to pre-defined closed-set paradigms, ignoring the challenges of real-world open-set scenarios. Such algorithms often falter in the presence of test samples originating from classes unseen during training phases. To tackle this problem, we introduce an innovative Open-Set Surgical Activity Recognition (OSSAR) framework. Our solution leverages the hyperspherical reciprocal point strategy to enhance the distinction between known and unknown classes in the feature space. Additionally, we address the issue of over-confidence in the closed set by refining model calibration, avoiding misclassification of unknown classes as known ones. To support our assertions, we establish an open-set surgical activity benchmark utilizing the public JIGSAWS dataset. Besides, we also collect a novel dataset on endoscopic submucosal dissection for surgical activity tasks. Extensive comparisons and ablation experiments on these datasets demonstrate the significant outperformance of our method over existing state-of-the-art approaches. Our proposed solution can effectively address the challenges of real-world surgical scenarios. Our code is publicly accessible at https://github.com/longbai1006/OSSAR.

Edward S. Hu, Jie Wang, Xingfang Yuan et al.

A robot's instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly acting to gain the missing information. Today's standard robot learning techniques struggle to produce such active perception behaviors. We propose a simple real-world robot learning recipe to efficiently train active perception policies. Our approach, asymmetric advantage weighted regression (AAWR), exploits access to "privileged" extra sensors at training time. The privileged sensors enable training high-quality privileged value functions that aid in estimating the advantage of the target policy. Bootstrapping from a small number of potentially suboptimal demonstrations and an easy-to-obtain coarse policy initialization, AAWR quickly acquires active perception behaviors and boosts task performance. In evaluations on 8 manipulation tasks on 3 robots spanning varying degrees of partial observability, AAWR synthesizes reliable active perception behaviors that outperform all prior approaches. When initialized with a "generalist" robot policy that struggles with active perception tasks, AAWR efficiently generates information-gathering behaviors that allow it to operate under severe partial observability for manipulation tasks. Website: https://penn-pal-lab.github.io/aawr/

Qianmei Liu, Yufei Kuang, Jie Wang

Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and improve the robustness of DRL. However, most of these approaches use a fixed parameter to control the intensity of the adversarial perturbation, which can lead to a trade-off between average performance and robustness. In fact, finding the optimal parameter of the perturbation is challenging, as excessive perturbations may destabilize training and compromise agent performance, while insufficient perturbations may not impart enough information to enhance robustness. To keep the training stable while improving robustness, we propose a simple but effective method, namely, Adaptive Adversarial Perturbation (A2P), which can dynamically select appropriate adversarial perturbations for each sample. Specifically, we propose an adaptive adversarial coefficient framework to adjust the effect of the adversarial perturbation during training. By designing a metric for the current intensity of the perturbation, our method can calculate the suitable perturbation levels based on the current relative performance. The appealing feature of our method is that it is simple to deploy in real-world applications and does not require accessing the simulator in advance. The experiments in MuJoCo show that our method can improve the training stability and learn a robust policy when migrated to different test environments. The code is available at https://github.com/Lqm00/A2P-SAC.

Haotian Ling, Zhihai Wang, Jie Wang

Cutting planes (cuts) play an important role in solving mixed-integer linear programs (MILPs), as they significantly tighten the dual bounds and improve the solving performance. A key problem for cuts is when to stop cuts generation, which is important for the efficiency of solving MILPs. However, many modern MILP solvers employ hard-coded heuristics to tackle this problem, which tends to neglect underlying patterns among MILPs from certain applications. To address this challenge, we formulate the cuts generation stopping problem as a reinforcement learning problem and propose a novel hybrid graph representation model (HYGRO) to learn effective stopping strategies. An appealing feature of HYGRO is that it can effectively capture both the dynamic and static features of MILPs, enabling dynamic decision-making for the stopping strategies. To the best of our knowledge, HYGRO is the first data-driven method to tackle the cuts generation stopping problem. By integrating our approach with modern solvers, experiments demonstrate that HYGRO significantly improves the efficiency of solving MILPs compared to competitive baselines, achieving up to 31% improvement.

Jie Wang, Youmin Zhang

This tutorial provides a systematic introduction to Gaussian process learning-based model predictive control (GP-MPC), an advanced approach integrating Gaussian process (GP) with model predictive control (MPC) for enhanced control in complex systems. It begins with GP regression fundamentals, illustrating how it enriches MPC with enhanced predictive accuracy and robust handling of uncertainties. A central contribution of this tutorial is the first detailed, systematic mathematical formulation of GP-MPC in literature, focusing on deriving the approximation of means and variances propagation for GP multi-step predictions. Practical applications in robotics control, such as path-following for mobile robots in challenging terrains and mixed-vehicle platooning, are discussed to demonstrate the real-world effectiveness and adaptability of GP-MPC. This tutorial aims to make GP-MPC accessible to researchers and practitioners, enriching the learning-based control field with in-depth theoretical and practical insights and fostering further innovations in complex system control.

Daiye Miao, Yufang Liu, Jie Wang et al.

LoRA has become one of the most widely used parameter-efficient fine-tuning methods due to its simplicity and effectiveness. However, numerous studies have shown that LoRA often introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning. Since identifying redundant parameters in LoRA is inherently difficult, how to eliminate them efficiently and accurately remains a challenging problem. In this paper, we propose TASO, a redundancy reduction method that leverages importance information from the pretrained model's weights to mitigate LoRA redundancy. Specifically, we estimate parameter importance on downstream tasks and identify task-specific core regions based on the distribution of importance scores. The location information of these core regions is then used to determine the sparse structure of LoRA modules, enabling redundancy removal before fine-tuning. Our approach significantly reduces the number of trainable parameters required for task adaptation, while providing a novel task-aligned perspective for LoRA redundancy reduction. Experimental results demonstrate that, with a parameter budget comparable to LoRA with rank $r = 1$, TASO consistently outperforms standard LoRA across multiple tasks, achieving strong fine-tuning performance while effectively eliminating redundant parameters.