arXiv subjects

Jie Zhang

Publications and source records attributed to Jie Zhang.

At least 793 records · Page 44Linked to original sources

arXiv2022

Learning Contextually Fused Audio-visual Representations for Audio-visual Speech Recognition

With the advance in self-supervised learning for audio and visual modalities, it has become possible to learn a robust audio-visual speech representation. This would be beneficial for improving the audio-visual speech recognition (AVSR) performance, as the multi-modal inputs contain more fruitful information in principle. In this paper, based on existing self-supervised representation learning methods for audio modality, we therefore propose an audio-visual representation learning approach. The proposed approach explores both the complementarity of audio-visual modalities and long-term context dependency using a transformer-based fusion module and a flexible masking strategy. After pre-training, the model is able to extract fused representations required by AVSR. Without loss of generality, it can be applied to single-modal tasks, e.g. audio/visual speech recognition by simply masking out one modality in the fusion module. The proposed pre-trained model is evaluated on speech recognition and lipreading tasks using one or two modalities, where the superiority is revealed.

eess.IV↗

arXiv2022

Wider: Scale Out Blockchain With Sharding by Account

The development of blockchain applications increased the demand for blockchain performance. Among the attempts of many blockchain scale-out solutions, sharding can improve performance and reduce the storage requirements of each node. Sharding enhances the throughput of the entire blockchain. Most sharding solutions have a fixed number of shards. We propose Wider chain with sharding by account. The number of shards is increased to unlimited. Meanwhile, Wider combines the idea of rollup and retains the main chain to confirm the status of the subchains. This design can avoid the Proof of Work computing power being scattered to the subchains and ensure the security of the blockchain.

cs.DC↗

arXiv2022

Physics-informed Deep Learning for Musculoskeletal Modelling: Predicting Muscle Forces and Joint Kinematics from Surface EMG

Musculoskeletal models have been widely used for detailed biomechanical analysis to characterise various functional impairments given their ability to estimate movement variables (i.e., muscle forces and joint moment) which cannot be readily measured in vivo. Physics-based computational neuromusculoskeletal models can interpret the dynamic interaction between neural drive to muscles, muscle dynamics, body and joint kinematics and kinetics. Still, such set of solutions suffers from slowness, especially for the complex models, hindering the utility in real-time applications. In recent years, data-driven methods has emerged as a promising alternative due to the benefits in speedy and simple implementation, but they cannot reflect the underlying neuromechanical processes. This paper proposes a physics-informed deep learning framework for musculoskeletal modelling, where physics-based domain knowledge is brought into the data-driven model as soft constraints to penalise/regularise the data-driven model. We use the synchronous muscle forces and joint kinematics prediction from surface electromyogram (sEMG) as the exemplar to illustrate the proposed framework. Convolutional neural network (CNN) is employed as the deep neural network to implement the proposed framework. At the same time, the physics law between muscle forces and joint kinematics is used the soft constraint. Experimental validations on two groups of data, including one benchmark dataset and one self-collected dataset from six healthy subjects, are performed. The experimental results demonstrate the effectiveness and robustness of the proposed framework.

eess.SP↗

arXiv2022

Do Loyal Users Enjoy Better Recommendations? Understanding Recommender Accuracy from a Time Perspective

In academic research, recommender systems are often evaluated on benchmark datasets, without much consideration about the global timeline. Hence, we are unable to answer questions like: Do loyal users enjoy better recommendations than non-loyal users? Loyalty can be defined by the time period a user has been active in a recommender system, or by the number of historical interactions a user has. In this paper, we offer a comprehensive analysis of recommendation results along global timeline. We conduct experiments with five widely used models, i.e., BPR, NeuMF, LightGCN, SASRec and TiSASRec, on four benchmark datasets, i.e., MovieLens-25M, Yelp, Amazon-music, and Amazon-electronic. Our experiment results give an answer "No" to the above question. Users with many historical interactions suffer from relatively poorer recommendations. Users who stay with the system for a shorter time period enjoy better recommendations. Both findings are counter-intuitive. Interestingly, users who have recently interacted with the system, with respect to the time point of the test instance, enjoy better recommendations. The finding on recency applies to all users, regardless of users' loyalty. Our study offers a different perspective to understand recommender accuracy, and our findings could trigger a revisit of recommender model design. The code is available in \url{https://github.com/putatu/recommenderLoyalty.

cs.IR↗

arXiv2022

On the Performance of Data Compression in Clustered Fog Radio Access Networks

The fog-radio-access-network (F-RAN) has been proposed to address the strict latency requirements, which offloads computation tasks generated in user equipments (UEs) to the edge to reduce the processing latency. However, it incorporates the task transmission latency, which may become the bottleneck of latency requirements. Data compression (DC) has been considered as one of the promising techniques to reduce the transmission latency. By compressing the computation tasks before transmitting, the transmission delay is reduced due to the shrink transmitted data size, and the original computing task can be retrieved by employing data decompressing (DD) at the edge nodes or the centre cloud. Nevertheless, the DC and DD incorporate extra processing latency, and the latency performance has not been investigated in the large-scale DC-enabled F-RAN. Therefore, in this work, the successful data compression probability (SDCP) is defined to analyse the latency performance of the F-RAN. Moreover, to analyse the effect of compression offloading ratio (COR), a novel hybrid compression mode is proposed based on the queueing theory. Based on this, the closed-form result of SDCP in the large-scale DC-enabled F-RAN is derived by combining the Matern cluster process and M/G/1 queueing model, and validated by Monte Carlo simulations. Based on the derived SDCP results, the effects of COR on the SDCP is analysed numerically. The results show that the SDCP with the optimal COR can be enhanced with a maximum value of 0.3 and 0.55 as compared with the cases of compressing all computing tasks at the edge and at the UE, respectively. Moreover, for the system requiring the minimal latency, the proposed hybrid compression mode can alleviate the requirement on the backhaul capacity.

eess.SP↗

arXiv2022

High-energy velocity tails in uniformly heated granular materials

We experimentally investigate the velocity distributions of quasi two-dimensional granular materials, which are homogeneously driven, i.e. uniformly heated, by an electromagnetic vibrator, where the translational velocity and the rotation of a single particle are Gaussian and independent. We observe the non-Gaussian distributions of particle velocity, with the density-independent high-energy tails characterized by an exponent of $β=1.50\pm0.03$ for volume fractions of $0.111\leϕ\le0.832$, covering a wide range of structures and dynamics. Surprisingly, our results are in excellent agreement with the prediction of the kinetic theories of granular gas, even for an extremely high volume fraction of $ϕ=0.832$ where the granular material forms a crystalline solid. Our experiment reveals that the density-independent high-energy velocity tails of $β=1.50$ are a fundamental property of uniformly heated granular matter.

cond-mat.soft↗

arXiv2022

DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation

Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison. We, therefore, conduct studies from the perspectives of practical theory and experiments, aiming at benchmarking recommendation for rigorous evaluation. Regarding the theoretical study, a series of hyper-factors affecting recommendation performance throughout the whole evaluation chain are systematically summarized and analyzed via an exhaustive review on 141 papers published at eight top-tier conferences within 2017-2020. We then classify them into model-independent and model-dependent hyper-factors, and different modes of rigorous evaluation are defined and discussed in-depth accordingly. For the experimental study, we release DaisyRec 2.0 library by integrating these hyper-factors to perform rigorous evaluation, whereby a holistic empirical study is conducted to unveil the impacts of different hyper-factors on recommendation performance. Supported by the theoretical and experimental studies, we finally create benchmarks for rigorous evaluation by proposing standardized procedures and providing performance of ten state-of-the-arts across six evaluation metrics on six datasets as a reference for later study. Overall, our work sheds light on the issues in recommendation evaluation, provides potential solutions for rigorous evaluation, and lays foundation for further investigation.

cs.IR↗

arXiv2022

Sampling Efficient Deep Reinforcement Learning through Preference-Guided Stochastic Exploration

Massive practical works addressed by Deep Q-network (DQN) algorithm have indicated that stochastic policy, despite its simplicity, is the most frequently used exploration approach. However, most existing stochastic exploration approaches either explore new actions heuristically regardless of Q-values or inevitably introduce bias into the learning process to couple the sampling with Q-values. In this paper, we propose a novel preference-guided $ε$-greedy exploration algorithm that can efficiently learn the action distribution in line with the landscape of Q-values for DQN without introducing additional bias. Specifically, we design a dual architecture consisting of two branches, one of which is a copy of DQN, namely the Q-branch. The other branch, which we call the preference branch, learns the action preference that the DQN implicit follows. We theoretically prove that the policy improvement theorem holds for the preference-guided $ε$-greedy policy and experimentally show that the inferred action preference distribution aligns with the landscape of corresponding Q-values. Consequently, preference-guided $ε$-greedy exploration motivates the DQN agent to take diverse actions, i.e., actions with larger Q-values can be sampled more frequently whereas actions with smaller Q-values still have a chance to be explored, thus encouraging the exploration. We assess the proposed method with four well-known DQN variants in nine different environments. Extensive results confirm the superiority of our proposed method in terms of performance and convergence speed. Index Terms- Preference-guided exploration, stochastic policy, data efficiency, deep reinforcement learning, deep Q-learning.

cs.LG↗

arXiv2022

Active Sampling for Min-Max Fairness

We propose simple active sampling and reweighting strategies for optimizing min-max fairness that can be applied to any classification or regression model learned via loss minimization. The key intuition behind our approach is to use at each timestep a datapoint from the group that is worst off under the current model for updating the model. The ease of implementation and the generality of our robust formulation make it an attractive option for improving model performance on disadvantaged groups. For convex learning problems, such as linear or logistic regression, we provide a fine-grained analysis, proving the rate of convergence to a min-max fair solution.

stat.ML↗

arXiv2022

Deep Auto-encoder with Neural Response

Artificial neural network (ANN) is a versatile tool to study the neural representation in the ventral visual stream, and the knowledge in neuroscience in return inspires ANN models to improve performance in the task. However, it is still unclear how to merge these two directions into a unified framework. In this study, we propose an integrated framework called Deep Autoencoder with Neural Response (DAE-NR), which incorporates information from ANN and the visual cortex to achieve better image reconstruction performance and higher neural representation similarity between biological and artificial neurons. The same visual stimuli (i.e., natural images) are input to both the mice brain and DAE-NR. The encoder of DAE-NR jointly learns the dependencies from neural spike encoding and image reconstruction. For the neural spike encoding task, the features derived from a specific hidden layer of the encoder are transformed by a mapping function to predict the ground-truth neural response under the constraint of image reconstruction. Simultaneously, for the image reconstruction task, the latent representation obtained by the encoder is assigned to a decoder to restore the original image under the guidance of neural information. In DAE-NR, the learning process of encoder, mapping function and decoder are all implicitly constrained by these two tasks. Our experiments demonstrate that if and only if with the joint learning, DAE-NRs can improve the performance of visual image reconstruction and increase the representation similarity between biological neurons and artificial neurons. The DAE-NR offers a new perspective on the integration of computer vision and neuroscience.

cs.LG↗

arXiv2022

Whale: Efficient Giant Model Training over Heterogeneous GPUs

The scaling up of deep neural networks has been demonstrated to be effective in improving model quality, but also encompasses several training challenges in terms of training efficiency, programmability, and resource adaptability. We present Whale, a general and efficient distributed training framework for giant models. To support various parallel strategies and their hybrids, Whale generalizes the programming interface by defining two new primitives in the form of model annotations, allowing for incorporating user hints. The Whale runtime utilizes those annotations and performs graph optimizations to transform a local deep learning DAG graph for distributed multi-GPU execution. Whale further introduces a novel hardware-aware parallel strategy, which improves the performance of model training on heterogeneous GPUs in a balanced manner. Deployed in a production cluster with 512 GPUs, Whale successfully trains an industry-scale multimodal model with over ten trillion model parameters, named M6, demonstrating great scalability and efficiency.

cs.DC↗

arXiv2022

Multivariate Sparse Group Lasso Joint Model for Radiogenomics Data

Radiogenomics is an emerging field in cancer research that combines medical imaging data with genomic data to predict patients clinical outcomes. In this paper, we propose a multivariate sparse group lasso joint model to integrate imaging and genomic data for building prediction models. Specifically, we jointly consider two models, one regresses imaging features on genomic features, and the other regresses patients clinical outcomes on genomic features. The regularization penalties through sparse group lasso allow incorporation of intrinsic group information, e.g. biological pathway and imaging category, to select both important intrinsic groups and important features within a group. To integrate information from the two models, in each model, we introduce a weight in the penalty term of each individual genomic feature, where the weight is inversely correlated with the model coefficient of that feature in the other model. This weight allows a feature to have a higher chance of selection by one model if it is selected by the other model. Our model is applicable to both continuous and time to event outcomes. It also allows the use of two separate datasets to fit the two models, addressing a practical challenge that many genomic datasets do not have imaging data available. Simulations and real data analyses demonstrate that our method outperforms existing methods in the literature.

stat.ME↗

arXiv2022

Calibration Strategy of the JUNO-TAO Experiment

The Taishan Antineutrino Observatory (JUNO-TAO, or TAO) is a satellite detector for the Jiangmen Underground Neutrino Observatory (JUNO). Located near the Taishan reactor, TAO independently measures the reactor's antineutrino energy spectrum with unprecedented energy resolution. To achieve this goal, energy response must be well calibrated. Using the Automated Calibration Unit (ACU) and the Cable Loop System (CLS) of TAO, multiple radioactive sources are deployed to various positions in the detector to perform a precise calibration of energy response. The non-linear energy response can be controlled within 0.6% with different energy points of these radioactive sources. It can be further improved by using $^{12}\rm B$ decay signals produced by cosmic muons. Through the energy non-uniformity calibration, residual non-uniformity is less than 0.2%. The energy resolution degradation and energy bias caused by the residual non-uniformity can be controlled within 0.05% and 0.3%, respectively. In addition, the stability of other detector parameters, such as the gain of each silicon photo-multiplier, can be monitored with a special ultraviolet LED calibration system.

physics.ins-det↗

arXiv2022

Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR

Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the other hand, it was shown that self-supervised pre-training enables the utilization of a large amount of unlabeled noisy data, which is rather beneficial for the noise robustness of ASR. However, the potential of the (optimal) integration of SE and self-supervised pre-training still remains unclear. In order to find an appropriate combination and reduce the impact of speech distortion caused by SE, in this paper we therefore propose a joint pre-training approach for the SE module and the self-supervised model. First, in the pre-training phase the original noisy waveform or the waveform obtained by SE is fed into the self-supervised model to learn the contextual representation, where the quantified clean speech acts as the target. Second, we propose a dual-attention fusion method to fuse the features of noisy and enhanced speeches, which can compensate the information loss caused by separately using individual modules. Due to the flexible exploitation of clean/noisy/enhanced branches, the proposed method turns out to be a generalization of some existing noise-robust ASR models, e.g., enhanced wav2vec2.0. Finally, experimental results on both synthetic and real noisy datasets show that the proposed joint training approach can improve the ASR performance under various noisy settings, leading to a stronger noise robustness.

eess.AS↗

arXiv2022

From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques

Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote health and well-beings, such as mental health and chronic cares. As the objectives of mobile sensing could be either \emph{(a) personalized medicine for individuals} or \emph{(b) public health for populations}, in this work we review the design of these mobile sensing apps, and propose to categorize the design of these apps/systems in two paradigms -- \emph{(i) Personal Sensing} and \emph{(ii) Crowd Sensing} paradigms. While both sensing paradigms might incorporate with common ubiquitous sensing technologies, such as wearable sensors, mobility monitoring, mobile data offloading, and/or cloud-based data analytics to collect and process sensing data from individuals, we present a novel taxonomy system with two major components that can specify and classify apps/systems from aspects of the life-cycle of mHealth Sensing: \emph{(1) Sensing Task Creation \& Participation}, \emph{(2) Health Surveillance \& Data Collection}, and \emph{(3) Data Analysis \& Knowledge Discovery}. With respect to different goals of the two paradigms, this work systematically reviews this field, and summarizes the design of typical apps/systems in the view of the configurations and interactions between these two components. In addition to summarization, the proposed taxonomy system also helps figure out the potential directions of mobile sensing for health from both personalized medicines and population health perspectives.

cs.LG↗

arXiv2022

Layer-wised Model Aggregation for Personalized Federated Learning

Personalized Federated Learning (pFL) not only can capture the common priors from broad range of distributed data, but also support customized models for heterogeneous clients. Researches over the past few years have applied the weighted aggregation manner to produce personalized models, where the weights are determined by calibrating the distance of the entire model parameters or loss values, and have yet to consider the layer-level impacts to the aggregation process, leading to lagged model convergence and inadequate personalization over non-IID datasets. In this paper, we propose a novel pFL training framework dubbed Layer-wised Personalized Federated learning (pFedLA) that can discern the importance of each layer from different clients, and thus is able to optimize the personalized model aggregation for clients with heterogeneous data. Specifically, we employ a dedicated hypernetwork per client on the server side, which is trained to identify the mutual contribution factors at layer granularity. Meanwhile, a parameterized mechanism is introduced to update the layer-wised aggregation weights to progressively exploit the inter-user similarity and realize accurate model personalization. Extensive experiments are conducted over different models and learning tasks, and we show that the proposed methods achieve significantly higher performance than state-of-the-art pFL methods.

cs.DC↗

arXiv2022

HINet: Half Instance Normalization Network for Image Restoration

In this paper, we explore the role of Instance Normalization in low-level vision tasks. Specifically, we present a novel block: Half Instance Normalization Block (HIN Block), to boost the performance of image restoration networks. Based on HIN Block, we design a simple and powerful multi-stage network named HINet, which consists of two subnetworks. With the help of HIN Block, HINet surpasses the state-of-the-art (SOTA) on various image restoration tasks. For image denoising, we exceed it 0.11dB and 0.28 dB in PSNR on SIDD dataset, with only 7.5% and 30% of its multiplier-accumulator operations (MACs), 6.8 times and 2.9 times speedup respectively. For image deblurring, we get comparable performance with 22.5% of its MACs and 3.3 times speedup on REDS and GoPro datasets. For image deraining, we exceed it by 0.3 dB in PSNR on the average result of multiple datasets with 1.4 times speedup. With HINet, we won 1st place on the NTIRE 2021 Image Deblurring Challenge - Track2. JPEG Artifacts, with a PSNR of 29.70. The code is available at https://github.com/megvii-model/HINet.

eess.IV↗

arXiv2022

High rectifying performance of heterojunctions with interface between armchair C$_3$N nanoribbons with and without edge H-passivation

Two-dimensional polyaniline with C$_3$N stoichiometry, is a newly fabricated layered material that has been expected to possess fascinating electronic, thermal, mechanical and chemical properties. The nature of its counterpart nano-ribbons/structures offering even more tunability in property because of the unique quantum confinement and edge effect, however, has not been revealed sufficiently. Here, using the first-principles calculation based on density functional theory and nonequilibrium Green's function technique, we first perform a study on the electron band structure of armchair C$_3$N nanoribbons (AC$_3$NNRs) without and with H-passivation. The calculated results show that the pristine AC$_3$NNRs are metal, while the H-passivated ones are either direct or indirect band gap semiconductors depending on the detailed edge atomic configurations. Then we propose a lateral planar homogenous junction with an interface between the pristine and H-passivated AC$_3$NNRs, in which forms a Schottky-like barrier. Interestingly, our further transport calculation demonstrates that this AC$_3$NNRs-based heterojunction exhibits a good rectification behavior. In specification, the average rectification ratio (RR) can reach up to $10^3$ in the bias regime from 0.2 to 0.4 V. Particularly, extending the length of semiconductor part in the heterojunction leads to the decrease of the current through the junction, but the RR can be enlarged obviously. The average RR increases to the order of $10^4$ in the bias from 0.25 to 0.40 V, with the boosted maximum up to $10^5$ at 0.35 V. The findings of this work may be serviceable for the design of functional nanodevices based on AC$_3$NNRs in the future.

cond-mat.mes-hall↗