Searcharxiv⌕ Search

arXiv subjects

Li Yu

Publications and source records attributed to Li Yu.

At least 109 records · Page 6Linked to original sources
arXiv2023

Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning

We study the budget allocation problem in online marketing campaigns that utilize previously collected offline data. We first discuss the long-term effect of optimizing marketing budget allocation decisions in the offline setting. To overcome the challenge, we propose a novel game-theoretic offline value-based reinforcement learning method using mixed policies. The proposed method reduces the need to store infinitely many policies in previous methods to only constantly many policies, which achieves nearly optimal policy efficiency, making it practical and favorable for industrial usage. We further show that this method is guaranteed to converge to the optimal policy, which cannot be achieved by previous value-based reinforcement learning methods for marketing budget allocation. Our experiments on a large-scale marketing campaign with tens-of-millions users and more than one billion budget verify the theoretical results and show that the proposed method outperforms various baseline methods. The proposed method has been successfully deployed to serve all the traffic of this marketing campaign.

cs.LG↗
arXiv2023

FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity

Federated noisy label learning (FNLL) is emerging as a promising tool for privacy-preserving multi-source decentralized learning. Existing research, relying on the assumption of class-balanced global data, might be incapable to model complicated label noise, especially in medical scenarios. In this paper, we first formulate a new and more realistic federated label noise problem where global data is class-imbalanced and label noise is heterogeneous, and then propose a two-stage framework named FedNoRo for noise-robust federated learning. Specifically, in the first stage of FedNoRo, per-class loss indicators followed by Gaussian Mixture Model are deployed for noisy client identification. In the second stage, knowledge distillation and a distance-aware aggregation function are jointly adopted for noise-robust federated model updating. Experimental results on the widely-used ICH and ISIC2019 datasets demonstrate the superiority of FedNoRo against the state-of-the-art FNLL methods for addressing class imbalance and label noise heterogeneity in real-world FL scenarios.

cs.LG↗
arXiv2023

FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image Classification

Federated learning (FL), training deep models from decentralized data without privacy leakage, has shown great potential in medical image computing recently. However, considering the ubiquitous class imbalance in medical data, FL can exhibit performance degradation, especially for minority classes (e.g. rare diseases). Existing methods towards this problem mainly focus on training a balanced classifier to eliminate class prior bias among classes, but neglect to explore better representation to facilitate classification performance. In this paper, we present a privacy-preserving FL method named FedIIC to combat class imbalance from two perspectives: feature learning and classifier learning. In feature learning, two levels of contrastive learning are designed to extract better class-specific features with imbalanced data in FL. In classifier learning, per-class margins are dynamically set according to real-time difficulty and class priors, which helps the model learn classes equally. Experimental results on publicly-available datasets demonstrate the superior performance of FedIIC in dealing with both real-world and simulated multi-source medical imaging data under class imbalance. Code is available at https://github.com/wnn2000/FedIIC.

cs.CV↗
arXiv2023

On equivariantly formal 2-torus manifolds

A 2-torus manifold is a closed connected smooth n-manifold with a non-free effective smooth $\mathbb{Z}^n_2$-action. In this paper, we prove that a 2-torus manifold is equivariantly formal if and only if the $\mathbb{Z}^n_2$-action is locally standard and every face of its orbit space (including the whole orbit space) is mod 2 acyclic. Our study is parallel to the study of torus manifolds with vanishing odd-degree cohomology by M. Masuda and T. Panov. As an application, we determine when such kind of 2-torus manifolds can have regular m-involutions (i.e. involutions with only isolated fixed points of the maximum possible number).

math.AT↗
arXiv2023

Instantaneous nonlocal quantum computation and circuit depth reduction

Instantaneous two-party quantum computation is a computation process with bipartite input and output, in which there are initial shared entanglement, and the nonlocal interactions are limited to simultaneous classical communication in both directions. It is almost equivalent to the problem of instantaneous measurements, and is related to some topics in quantum foundations and position-based quantum cryptography. In the first part of this work, we show that a particular simplified subprocedure, known as a garden-hose gadget, cannot significantly reduce the entanglement cost in instantaneous two-party quantum computation. In the second part, we show that any unitary circuit consisting of layers of Clifford gates and T gates can be implemented using a circuit with measurements (or a unitary circuit) of depth proportional to the T-depth of the original circuit. This result has some similarity with and also some difference from a result in measurement-based quantum computation. It is of limited use since interesting quantum algorithms often require a high ratio of T gates, but still we discuss its extensions and applications.

quant-ph↗
arXiv2023

Carbon emissions and sustainability of launching 5G mobile networks in China

Since 2021, China has deployed more than 2.1 million 5G base stations to increase the network capacity and provide ubiquitous digital connectivity for mobile terminals. However, the launch of 5G networks also exacerbates the misalignment between cellular traffic and energy consumption, which reduces carbon efficiency - the amount of network traffic that can be delivered for each unit of carbon emission. In this study, we develop a large-scale data-driven framework to estimate the carbon emissions induced by mobile networks. We show that the decline in carbon efficiency leads to a carbon efficiency trap, estimated to cause additional carbon emissions of 23.82 +- 1.07 megatons in China. To mitigate the misalignment and improve energy efficiency, we propose DeepEnergy, an energy-saving method leveraging collaborative deep reinforcement learning and graph neural networks. DeepEnergy models complex collaboration among cells, making it possible to effectively coordinate the working state of tens of thousands of cells, which could help over 71% of Chinese provinces avoid carbon efficiency traps. In addition, applying DeepEnergy is estimated to reduce 20.90 +- 0.98 megatons of carbon emissions at the national level in 2023. We further assess the effects of adopting renewable energy and discover that the mobile network could accomplish more than 50% of its net-zero goal by integrating DeepEnergy and solar energy systems. Our study provides insight into carbon emission mitigation in 5G network infrastructure launching in China and overworld, paving the way towards achieving sustainable development goals and future net-zero mobile networks.

eess.SY↗
arXiv2023

Hand Gesture Recognition through Reflected Infrared Light Wave Signals

In this study, we present a wireless (non-contact) gesture recognition method using only incoherent light wave signals reflected from a human subject. In comparison to existing radar, light shadow, sound and camera-based sensing systems, this technology uses a low-cost ubiquitous light source (e.g., infrared LED) to send light towards the subject's hand performing gestures and the reflected light is collected by a light sensor (e.g., photodetector). This light wave sensing system recognizes different gestures from the variations of the received light intensity within a 20-35cm range. The hand gesture recognition results demonstrate up to 96% accuracy on average. The developed system can be utilized in numerous Human-computer Interaction (HCI) applications as a low-cost and non-contact gesture recognition technology.

eess.SP↗
arXiv2023

DataAI-6G: A System Parameters Configurable Channel Dataset for AI-6G Research

With the acceleration of the commercialization of fifth generation (5G) mobile communication technology and the research for 6G communication systems, the communication system has the characteristics of high frequency, multi-band, high speed movement of users and large antenna array. These bring many difficulties to obtain accurate channel state information (CSI), which makes the performance of traditional communication methods be greatly restricted. Therefore, there has been a lot of interest in using artificial intelligence (AI) instead of traditional methods to improve performance. A common and accurate dataset is essential for the research of AI communication. However, the common datasets nowadays still lack some important features, such as mobile features, spatial non-stationary features etc. To address these issues, we give a dataset for future 6G communication. In this dataset, we address these issues with specific simulation methods and accompanying code processing.

eess.SP↗
arXiv2023

Spatiotemporally Consistent HDR Indoor Lighting Estimation

We propose a physically-motivated deep learning framework to solve a general version of the challenging indoor lighting estimation problem. Given a single LDR image with a depth map, our method predicts spatially consistent lighting at any given image position. Particularly, when the input is an LDR video sequence, our framework not only progressively refines the lighting prediction as it sees more regions, but also preserves temporal consistency by keeping the refinement smooth. Our framework reconstructs a spherical Gaussian lighting volume (SGLV) through a tailored 3D encoder-decoder, which enables spatially consistent lighting prediction through volume ray tracing, a hybrid blending network for detailed environment maps, an in-network Monte-Carlo rendering layer to enhance photorealism for virtual object insertion, and recurrent neural networks (RNN) to achieve temporally consistent lighting prediction with a video sequence as the input. For training, we significantly enhance the OpenRooms public dataset of photorealistic synthetic indoor scenes with around 360K HDR environment maps of much higher resolution and 38K video sequences, rendered with GPU-based path tracing. Experiments show that our framework achieves lighting prediction with higher quality compared to state-of-the-art single-image or video-based methods, leading to photorealistic AR applications such as object insertion.

cs.CV↗
arXiv2023

BATFormer: Towards Boundary-Aware Lightweight Transformer for Efficient Medical Image Segmentation

Objective: Transformers, born to remedy the inadequate receptive fields of CNNs, have drawn explosive attention recently. However, the daunting computational complexity of global representation learning, together with rigid window partitioning, hinders their deployment in medical image segmentation. This work aims to address the above two issues in transformers for better medical image segmentation. Methods: We propose a boundary-aware lightweight transformer (BATFormer) that can build cross-scale global interaction with lower computational complexity and generate windows flexibly under the guidance of entropy. Specifically, to fully explore the benefits of transformers in long-range dependency establishment, a cross-scale global transformer (CGT) module is introduced to jointly utilize multiple small-scale feature maps for richer global features with lower computational complexity. Given the importance of shape modeling in medical image segmentation, a boundary-aware local transformer (BLT) module is constructed. Different from rigid window partitioning in vanilla transformers which would produce boundary distortion, BLT adopts an adaptive window partitioning scheme under the guidance of entropy for both computational complexity reduction and shape preservation. Results: BATFormer achieves the best performance in Dice of 92.84%, 91.97%, 90.26%, and 96.30% for the average, right ventricle, myocardium, and left ventricle respectively on the ACDC dataset and the best performance in Dice, IoU, and ACC of 90.76%, 84.64%, and 96.76% respectively on the ISIC 2018 dataset. More importantly, BATFormer requires the least amount of model parameters and the lowest computational complexity compared to the state-of-the-art approaches. Conclusion and Significance: Our results demonstrate the necessity of developing customized transformers for efficient and better medical image segmentation.

cs.CV↗
arXiv2023

Remote State Estimation with Posterior-Based Stochastic Event-Triggered Schedule

This paper aims to study the state estimation problem under the stochastic event-triggered (SET) schedule. A posterior-based SET mechanism is proposed, which determines whether to transmit data by the effect of the measurement on the posterior estimate. Since this SET mechanism considers the whole posterior probability density function, it has better information screening capability and utilization than the existing SET mechanisms that only consider the first-order moment information of measurement and prior estimate. Then, based on the proposed SET mechanism, the corresponding exact minimum mean square error estimator is derived by Bayes rule. Moreover, the prediction error covariance of the estimator is proved to be bounded under moderate conditions. Meanwhile, the upper and lower bounds on the average communication rate are also analyzed. Finally, two different systems are employed to show the effectiveness and advantages of the proposed methods.

eess.SY↗
arXiv2023

Cross-Fusion Rule for Personalized Federated Learning

Data scarcity and heterogeneity pose significant performance challenges for personalized federated learning, and these challenges are mainly reflected in overfitting and low precision in existing methods. To overcome these challenges, a multi-layer multi-fusion strategy framework is proposed in this paper, i.e., the server adopts the network layer parameters of each client upload model as the basic unit of fusion for information-sharing calculation. Then, a new fusion strategy combining personalized and generic is purposefully proposed, and the network layer number fusion threshold of each fusion strategy is designed according to the network layer function. Under this mechanism, the L2-Norm negative exponential similarity metric is employed to calculate the fusion weights of the corresponding feature extraction layer parameters for each client, thus improving the efficiency of heterogeneous data personalized collaboration. Meanwhile, the federated global optimal model approximation fusion strategy is adopted in the network full-connect layer, and this generic fusion strategy alleviates the overfitting introduced by forceful personalized. Finally, the experimental results show that the proposed method is superior to the state-of-the-art methods.

cs.LG↗
arXiv2023

Learning stability of partially observed switched linear systems

This paper deals with learning stability of partially observed switched linear systems under arbitrary switching. Such systems are widely used to describe cyber-physical systems which arise by combining physical systems with digital components. In many real-world applications, the internal states cannot be observed directly. It is thus more realistic to conduct system analysis using the outputs of the system. Stability is one of the most frequent requirement for safety and robustness of cyber-physical systems. Existing methods for analyzing stability of switched linear systems often require the knowledge of the parameters and/or all the states of the underlying system. In this paper, we propose an algorithm for deciding stability of switched linear systems under arbitrary switching based purely on observed output data. The proposed algorithm essentially relies on an output-based Lyapunov stability framework and returns an estimate of the joint spectral radius (JSR). We also prove a probably approximately correct error bound on the quality of the estimate of the JSR from the perspective of statistical learning theory.

eess.SY↗
arXiv2022

Secure Fusion Estimation Against FDI Sensor Attacks in Cyber-Physical Systems

This paper is concerned with the problem of secure multi-sensors fusion estimation for cyber-physical systems, where sensor measurements may be tampered with by false data injection (FDI) attacks. In this work, it is considered that the adversary may not be able to attack all sensors. That is, several sensors remain not being attacked. In this case, new local reorganized subsystems including the FDI attack signals and un-attacked sensor measurements are constructed by the augmentation method. Then, a joint Kalman fusion estimator is designed under linear minimum variance sense to estimate the system state and FDI attack signals simultaneously. Finally, illustrative examples are employed to show the effectiveness and advantages of the proposed methods.

eess.SY↗
arXiv2022

End-to-end Transformer for Compressed Video Quality Enhancement

Convolutional neural networks have achieved excellent results in compressed video quality enhancement task in recent years. State-of-the-art methods explore the spatiotemporal information of adjacent frames mainly by deformable convolution. However, offset fields in deformable convolution are difficult to train, and its instability in training often leads to offset overflow, which reduce the efficiency of correlation modeling. In this work, we propose a transformer-based compressed video quality enhancement (TVQE) method, consisting of Swin-AutoEncoder based Spatio-Temporal feature Fusion (SSTF) module and Channel-wise Attention based Quality Enhancement (CAQE) module. The proposed SSTF module learns both local and global features with the help of Swin-AutoEncoder, which improves the ability of correlation modeling. Meanwhile, the window mechanism-based Swin Transformer and the encoderdecoder structure greatly improve the execution efficiency. On the other hand, the proposed CAQE module calculates the channel attention, which aggregates the temporal information between channels in the feature map, and finally achieves the efficient fusion of inter-frame information. Extensive experimental results on the JCT-VT test sequences show that the proposed method achieves better performance in average for both subjective and objective quality. Meanwhile, our proposed method outperforms existing ones in terms of both inference speed and GPU consumption.

cs.MM↗
arXiv2022

How to Define the Propagation Environment Semantics and Its Application in Scatterer-Based Beam Prediction

In view of the propagation environment directly determining the channel fading, the application tasks can also be solved with the aid of the environment information. Inspired by task-oriented semantic communication and machine learning (ML) powered environment-channel mapping methods, this work aims to provide a new view of the environment from the semantic level, which defines the propagation environment semantics (PES) as a limited set of propagation environment semantic symbols (PESS) for diverse application tasks. The PESS is extracted oriented to the tasks with channel properties as a foundation. For method validation, the PES-aided beam prediction (PESaBP) is presented in non-line-of-sight (NLOS). The PESS of environment features and graphs are given for the semantic actions of channel quality evaluation and target scatterer detection of maximum power, which can obtain 0.92 and 0.9 precision, respectively, and save over 87% of time cost.

eess.SP↗
arXiv2022

Classification of Schmidt-rank-two multipartite unitary gates by singular number

The multipartite unitary gates are called genuine if they are not product unitary operators across any bipartition. We mainly investigate the classification of genuine multipartite unitary gates of Schmidt rank two, by focusing on the multiqubit scenario. For genuine multipartite (excluding bipartite) unitary gates of Schmidt rank two, there is an essential fact that their Schmidt decompositions are unique. Based on this fact, we propose a key notion named as singular number to classify the unitary gates concerned. The singular number is defined as the number of local singular operators in the Schmidt decomposition. We then determine the accurate range of singular number. For each singular number, we formulate the parametric Schmidt decompositions of genuine multiqubit unitary gates under local equivalence. Finally, we extend the study to three-qubit diagonal unitary gates due to the close relation between diagonal unitary gates and Schmidt-rank-two unitaries. We start with discussing two typical examples of Schmidt rank two, one of which is a fundamental three-qubit unitary gate, i.e., the CCZ gate. Then we characterize the diagonal unitary gates of Schmidt rank greater than two. We show that a three-qubit diagonal unitary gate has Schmidt rank at most three, and present a necessary and sufficient condition for such a unitary gate of Schmidt rank three. This completes the characterization of all genuine three-qubit diagonal unitary gates.

quant-ph↗
arXiv2022

Distributed Event-Triggered Nonlinear Fusion Estimation under Resource Constraints

This paper studies the event-triggered distributed fusion estimation problems for a class of nonlinear networked multisensor fusion systems without noise statistical characteristics. When considering the limited resource problems of two kinds of communication channels (i.e., sensor-to-remote estimator channel and smart sensor-to-fusion center channel), an event-triggered strategy and a dimensionality reduction strategy are introduced in a unified networked framework to lighten the communication burden. Then, two kinds of compensation strategies in terms of a unified model are designed to restructure the untransmitted information, and the local/fusion estimators are proposed based on the compensation information. Furthermore, the linearization errors caused by the Taylor expansion are modeled by the state-dependent matrices with uncertain parameters when establishing estimation error systems, and then different robust recursive optimization problems are constructed to determine the estimator gains and the fusion criteria. Meanwhile, the stability conditions are also proposed such that the square errors of the designed nonlinear estimators are bounded. Finally, a vehicle localization system is employed to demonstrate the effectiveness and advantages of the proposed methods.

eess.SY↗