arXiv subjects

Lei Cheng

Publications and source records attributed to Lei Cheng.

At least 91 records · Page 5Linked to original sources

arXiv2022

Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks

Classification of long sequential data is an important Machine Learning task and appears in many application scenarios. Recurrent Neural Networks, Transformers, and Convolutional Neural Networks are three major techniques for learning from sequential data. Among these methods, Temporal Convolutional Networks (TCNs) which are scalable to very long sequences have achieved remarkable progress in time series regression. However, the performance of TCNs for sequence classification is not satisfactory because they use a skewed connection protocol and output classes at the last position. Such asymmetry restricts their performance for classification which depends on the whole sequence. In this work, we propose a symmetric multi-scale architecture called Circular Dilated Convolutional Neural Network (CDIL-CNN), where every position has an equal chance to receive information from other positions at the previous layers. Our model gives classification logits in all positions, and we can apply a simple ensemble learning to achieve a better decision. We have tested CDIL-CNN on various long sequential datasets. The experimental results show that our method has superior performance over many state-of-the-art approaches.

cs.LG↗

arXiv2022

Tensor Train Factorization and Completion under Noisy Data with Prior Analysis and Rank Estimation

Tensor train (TT) decomposition, a powerful tool for analyzing multidimensional data, exhibits superior performance in many machine learning tasks. However, existing methods for TT decomposition either suffer from noise overfitting, or require extensive fine-tuning of the balance between model complexity and representation accuracy. In this paper, a fully Bayesian treatment of TT decomposition is employed to avoid noise overfitting, by endowing it with the ability of automatic rank determination. In particular, theoretical evidence is established for adopting a Gaussian-product-Gamma prior to induce sparsity on the slices of the TT cores, so that the model complexity is automatically determined even under incomplete and noisy observed data. Furthermore, based on the proposed probabilistic model, an efficient learning algorithm is derived under the variational inference framework. Simulation results on synthetic data show the success of the proposed model and algorithm in recovering the ground-truth TT structure from incomplete noisy data. Further experiments on real-world data demonstrate the proposed algorithm performs better in image completion and image classification, compared to other existing TT decomposition algorithms.

eess.SP↗

arXiv2022

Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention

Self-Attention is a widely used building block in neural modeling to mix long-range data elements. Most self-attention neural networks employ pairwise dot-products to specify the attention coefficients. However, these methods require $O(N^2)$ computing cost for sequence length $N$. Even though some approximation methods have been introduced to relieve the quadratic cost, the performance of the dot-product approach is still bottlenecked by the low-rank constraint in the attention matrix factorization. In this paper, we propose a novel scalable and effective mixing building block called Paramixer. Our method factorizes the interaction matrix into several sparse matrices, where we parameterize the non-zero entries by MLPs with the data elements as input. The overall computing cost of the new building block is as low as $O(N \log N)$. Moreover, all factorizing matrices in Paramixer are full-rank, so it does not suffer from the low-rank bottleneck. We have tested the new method on both synthetic and various real-world long sequential data sets and compared it with several state-of-the-art attention networks. The experimental results show that Paramixer has better performance in most learning tasks.

cs.LG↗

arXiv2022

Towards Flexible Sparsity-Aware Modeling: Automatic Tensor Rank Learning Using The Generalized Hyperbolic Prior

Tensor rank learning for canonical polyadic decomposition (CPD) has long been deemed as an essential yet challenging problem. In particular, since the tensor rank controls the complexity of the CPD model, its inaccurate learning would cause overfitting to noise or underfitting to the signal sources, and even destroy the interpretability of model parameters. However, the optimal determination of a tensor rank is known to be a non-deterministic polynomial-time hard (NP-hard) task. Rather than exhaustively searching for the best tensor rank via trial-and-error experiments, Bayesian inference under the Gaussian-gamma prior was introduced in the context of probabilistic CPD modeling, and it was shown to be an effective strategy for automatic tensor rank determination. This triggered flourishing research on other structured tensor CPDs with automatic tensor rank learning. On the other side of the coin, these research works also reveal that the Gaussian-gamma model does not perform well for high-rank tensors and/or low signal-to-noise ratios (SNRs). To overcome these drawbacks, in this paper, we introduce a more advanced generalized hyperbolic (GH) prior to the probabilistic CPD model, which not only includes the Gaussian-gamma model as a special case, but also is more flexible to adapt to different levels of sparsity. Based on this novel probabilistic model, an algorithm is developed under the framework of variational inference, where each update is obtained in a closed-form. Extensive numerical results, using synthetic data and real-world datasets, demonstrate the significantly improved performance of the proposed method in learning both low as well as high tensor ranks even for low SNR cases.

cs.LG↗

arXiv2022

Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search

Neural networks often encounter various stringent resource constraints while deploying on edge devices. To tackle these problems with less human efforts, automated machine learning becomes popular in finding various neural architectures that fit diverse Artificial Intelligence of Things (AIoT) scenarios. Recently, to prevent the leakage of private information while enable automated machine intelligence, there is an emerging trend to integrate federated learning and neural architecture search (NAS). Although promising as it may seem, the coupling of difficulties from both tenets makes the algorithm development quite challenging. In particular, how to efficiently search the optimal neural architecture directly from massive non-independent and identically distributed (non-IID) data among AIoT devices in a federated manner is a hard nut to crack. In this paper, to tackle this challenge, by leveraging the advances in ProxylessNAS, we propose a Federated Direct Neural Architecture Search (FDNAS) framework that allows for hardware-friendly NAS from non- IID data across devices. To further adapt to both various data distributions and different types of devices with heterogeneous embedded hardware platforms, inspired by meta-learning, a Cluster Federated Direct Neural Architecture Search (CFDNAS) framework is proposed to achieve device-aware NAS, in the sense that each device can learn a tailored deep learning model for its particular data distribution and hardware constraint. Extensive experiments on non-IID datasets have shown the state-of-the-art accuracy-efficiency trade-offs achieved by the proposed solution in the presence of both data and device heterogeneity.

cs.LG↗

arXiv2022

Tensor-based Basis Function Learning for Three-dimensional Sound Speed Fields

Basis function learning is the stepping stone towards effective three-dimensional (3D) sound speed field (SSF) inversion for various acoustic signal processing tasks, including ocean acoustic tomography, underwater target localization/tracking, and underwater communications. Classical basis functions include the empirical orthogonal functions (EOFs), Fourier basis functions, and their combinations. The unsupervised machine learning method, e.g., the K-SVD algorithm, has recently tapped into the basis function design, showing better representation performance than the EOFs. However, existing methods do not consider basis function learning approaches that treat 3D SSF data as a third-order tensor, and thus cannot fully utilize the 3D interactions/correlations therein. To circumvent such a drawback, basis function learning is linked to tensor decomposition in this paper, which is the primary drive for recent multi-dimensional data mining. In particular, a tensor-based basis function learning framework is proposed, which can include the classical basis functions (using EOFs and/or Fourier basis functions) as its special cases. This provides a unified tensor perspective for understanding and representing 3D SSFs. Numerical results using the South China Sea 3D SSF data have demonstrated the excellent performance of the tensor-based basis functions.

eess.SP↗

arXiv2021

Training Time Minimization for Federated Edge Learning with Optimized Gradient Quantization and Bandwidth Allocation

Training a machine learning model with federated edge learning (FEEL) is typically time-consuming due to the constrained computation power of edge devices and limited wireless resources in edge networks. In this paper, the training time minimization problem is investigated in a quantized FEEL system, where the heterogeneous edge devices send quantized gradients to the edge server via orthogonal channels. In particular, a stochastic quantization scheme is adopted for compression of uploaded gradients, which can reduce the burden of per-round communication but may come at the cost of increasing number of communication rounds. The training time is modeled by taking into account the communication time, computation time and the number of communication rounds. Based on the proposed training time model, the intrinsic trade-off between the number of communication rounds and per-round latency is characterized. Specifically, we analyze the convergence behavior of the quantized FEEL in terms of the optimality gap. Further, a joint data-and-model-driven fitting method is proposed to obtain the exact optimality gap, based on which the closed-form expressions for the number of communication rounds and the total training time are obtained. Constrained by total bandwidth, the training time minimization problem is formulated as a joint quantization level and bandwidth allocation optimization problem. To this end, an algorithm based on alternating optimization is proposed, which alternatively solves the subproblem of quantization optimization via successive convex approximation and the subproblem of bandwidth allocation via bisection search. With different learning tasks and models, the validation of our analysis and the near-optimal performance of the proposed optimization algorithm are demonstrated by the experimental results.

cs.IT↗

arXiv2021

RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation

Cross-domain recommendation can help alleviate the data sparsity issue in traditional sequential recommender systems. In this paper, we propose the RecGURU algorithm framework to generate a Generalized User Representation (GUR) incorporating user information across domains in sequential recommendation, even when there is minimum or no common users in the two domains. We propose a self-attentive autoencoder to derive latent user representations, and a domain discriminator, which aims to predict the origin domain of a generated latent representation. We propose a novel adversarial learning method to train the two modules to unify user embeddings generated from different domains into a single global GUR for each user. The learned GUR captures the overall preferences and characteristics of a user and thus can be used to augment the behavior data and improve recommendations in any single domain in which the user is involved. Extensive experiments have been conducted on two public cross-domain recommendation datasets as well as a large dataset collected from real-world applications. The results demonstrate that RecGURU boosts performance and outperforms various state-of-the-art sequential recommendation and cross-domain recommendation methods. The collected data will be released to facilitate future research.

cs.IR↗

arXiv2021

Sparse Factorization of Large Square Matrices

Square matrices appear in many machine learning problems and models. Optimization over a large square matrix is expensive in memory and in time. Therefore an economic approximation is needed. Conventional approximation approaches factorize the square matrix into a number matrices of much lower ranks. However, the low-rank constraint is a performance bottleneck if the approximated matrix is intrinsically high-rank or close to full rank. In this paper, we propose to approximate a large square matrix with a product of sparse full-rank matrices. In the approximation, our method needs only $N(\log N)^2$ non-zero numbers for an $N\times N$ full matrix. We present both non-parametric and parametric ways to find the factorization. In the former, we learn the factorizing matrices directly, and in the latter, we train neural networks to map input data to the non-zero matrix entries. The sparse factorization method is tested for a variety of synthetic and real-world square matrices. The experimental results demonstrate that our method gives a better approximation when the approximated matrix is sparse and high-rank. Based on this finding, we use our parametric method as a scalable attention architecture that performs strongly in learning tasks for long sequential data and defeats Transformer and its several variants.

cs.LG↗

arXiv2021

A Bayesian Tensor Approach to Enable RIS for 6G Massive Unsourced Random Access

This paper investigates the problem of joint massive devices separation and channel estimation for a reconfigurable intelligent surface (RIS)-aided unsourced random access (URA) scheme in the sixth-generation (6G) wireless networks. In particular, by associating the data sequences to a rank-one tensor and exploiting the angular sparsity of the channel, the detection problem is cast as a high-order coupled tensor decomposition problem. However, the coupling among multiple devices to RIS (device-RIS) channels together with their sparse structure make the problem intractable. By devising novel priors to incorporate problem structures, we design a novel probabilistic model to capture both the element-wise sparsity from the angular channel model and the low rank property due to the sporadic nature of URA. Based on the this probabilistic model, we develop a coupled tensor-based automatic detection (CTAD) algorithm under the framework of variational inference with fast convergence and low computational complexity. Moreover, the proposed algorithm can automatically learn the number of active devices and thus effectively avoid noise overfitting. Extensive simulation results confirm the effectiveness and improvements of the proposed URA algorithm in large-scale RIS regime.

cs.IT↗

arXiv2021

Similarity Embedding Networks for Robust Human Activity Recognition

Deep learning models for human activity recognition (HAR) based on sensor data have been heavily studied recently. However, the generalization ability of deep models on complex real-world HAR data is limited by the availability of high-quality labeled activity data, which are hard to obtain. In this paper, we design a similarity embedding neural network that maps input sensor signals onto real vectors through carefully designed convolutional and LSTM layers. The embedding network is trained with a pairwise similarity loss, encouraging the clustering of samples from the same class in the embedded real space, and can be effectively trained on a small dataset and even on a noisy dataset with mislabeled samples. Based on the learned embeddings, we further propose both nonparametric and parametric approaches for activity recognition. Extensive evaluation based on two public datasets has shown that the proposed similarity embedding network significantly outperforms state-of-the-art deep models on HAR classification tasks, is robust to mislabeled samples in the training set, and can also be used to effectively denoise a noisy dataset.

cs.CV↗

arXiv2021

Towards Overfitting Avoidance: Tuning-free Tensor-aided Multi-user Channel Estimation for 3D Massive MIMO Communications

Channel estimation has long been deemed as one of the most critical problems in three-dimensional (3D) massive multiple-input multiple-output (MIMO), which is recognized as the leading technology that enables 3D spatial signal processing in the fifth-generation (5G) wireless communications and beyond. Recently, by exploring the angular channel model and tensor decompositions, the accuracy of single-user channel estimation for 3D massive MIMO communications has been significantly improved given a limited number of pilot signals. However, these existing approaches cannot be straightforwardly extended to the multi-user channel estimation task, where the base station (BS) aims at acquiring the channels of multiple users at the same time. The difficulty is that the coupling among multiple users' channels makes the channel estimation deviate from widely-used tensor decompositions. It gives a non-standard tensor decomposition format that has not been well tackled. To overcome this challenge, besides directly fitting the new tensor model for channel estimation to the wireless data via block coordinate descent (BCD) method, which is prone to the overfitting of noises or requires regularization parameter tuning, we further propose a novel tuning-free channel estimation algorithm that can automatically control the channel model complexity and thus effectively avoid the overfitting. Numerical results are presented to demonstrate the excellent performance of the proposed algorithm in terms of both estimation accuracy and overfitting avoidance.

eess.SP↗

arXiv2020

FDNAS: Improving Data Privacy and Model Diversity in AutoML

To prevent the leakage of private information while enabling automated machine intelligence, there is an emerging trend to integrate federated learning and Neural Architecture Search (NAS). Although promising as it may seem, the coupling of difficulties from both two tenets makes the algorithm development quite challenging. In particular, how to efficiently search the optimal neural architecture directly from massive non-iid data of clients in a federated manner remains to be a hard nut to crack. To tackle this challenge, in this paper, by leveraging the advances in proxy-less NAS, we propose a Federated Direct Neural Architecture Search (FDNAS) framework that allows hardware-aware NAS from decentralized non-iid data of clients. To further adapt for various data distributions of clients, inspired by meta-learning, a cluster Federated Direct Neural Architecture Search (CFDNAS) framework is proposed to achieve client-aware NAS, in the sense that each client can learn a tailored deep learning model for its particular data distribution. Extensive experiments on real-world non-iid datasets show state-of-the-art accuracy-efficiency trade-offs for various hardware and data distributions of clients. Our codes will be released publicly upon paper acceptance.

cs.LG↗

arXiv2020

Pushing The Limit of Type I Codebook For FDD Massive MIMO Beamforming: A Channel Covariance Reconstruction Approach

There is a fundamental trade-off between the channel representation resolution of codebooks and the overheads of feedback communications in the fifth generation new radio (5G NR) frequency division duplex (FDD) massive multiple-input and multiple-output (MIMO) systems. In particular, two types of codebooks (namely Type I and Type II codebooks) are introduced with different resolution and overhead requirements. Although the Type I codebook based scheme requires lower feedback overhead, its channel state information (CSI) reconstruction and beamforming performance are not as good as those from the Type II codebook based scheme. However, since the Type I codebook based scheme has been widely used in 4G systems for many years, replacing it by the Type II codebook based scheme overnight is too costly to be an option. Therefore, in this paper, using Type I codebook, we leverage advances in cutting plane method to optimize the CSI reconstruction at the base station (BS), in order to close the gap between these two codebook based beamforming schemes. Numerical results based on channel samples from QUAsi Deterministic RadIo channel GenerAtor (QuaDRiGa) are presented to show the excellent performance of the proposed algorithm in terms of beamforming vector acquisition.

eess.SP↗

arXiv2020

Edge Learning with Unmanned Ground Vehicle: Joint Path, Energy and Sample Size Planning

Edge learning (EL), which uses edge computing as a platform to execute machine learning algorithms, is able to fully exploit the massive sensing data generated by Internet of Things (IoT). However, due to the limited transmit power at IoT devices, collecting the sensing data in EL systems is a challenging task. To address this challenge, this paper proposes to integrate unmanned ground vehicle (UGV) with EL. With such a scheme, the UGV could improve the communication quality by approaching various IoT devices. However, different devices may transmit different data for different machine learning jobs and a fundamental question is how to jointly plan the UGV path, the devices' energy consumption, and the number of samples for different jobs? This paper further proposes a graph-based path planning model, a network energy consumption model and a sample size planning model that characterizes F-measure as a function of the minority class sample size. With these models, the joint path, energy and sample size planning (JPESP) problem is formulated as a large-scale mixed integer nonlinear programming (MINLP) problem, which is nontrivial to solve due to the high-dimensional discontinuous variables related to UGV movement. To this end, it is proved that each IoT device should be served only once along the path, thus the problem dimension is significantly reduced. Furthermore, to handle the discontinuous variables, a tabu search (TS) based algorithm is derived, which converges in expectation to the optimal solution to the JPESP problem. Simulation results under different task scenarios show that our optimization schemes outperform the fixed EL and the full path EL schemes.

eess.SP↗

arXiv2020

A Covariance-based User Activity Detection and Channel Estimation Approach with Novel Pilot Design

This paper studies the massive machine-type communications (mMTC) for the future Internet of Things (IoT) applications, where a large number of IoT devices exist in the network and a random subset of them become active at each time instant. Building upon the fact that the covariance matrix of the received signal can be accurately estimated in the spatial domain if the base station (BS) is equipped with a massive number of antennas, we propose a covariance-based device activity detection and channel estimation strategy in a massive MIMO (multiple-input multiple-output) aided mMTC system. For this strategy, a novel approach for the pilot sequence design is first provided, where the pilot of each device is merely determined by a unique phase parameter. Then, by estimating the phase parameters of the active pilot sequences that contribute to the received covariance matrix, an efficient algorithm is proposed to detect the active devices without the prior information about the total number of active devices. At last, given the estimation of active devices, channel estimation is conducted based on the conventional minimum mean-squared error (MMSE) approach. It is worth noting that our proposed strategy is able to obtain all the results in closed-forms, and is thus of much lower complexity compared to the existing strategies that are based on iterative algorithms for device detection and channel estimation.

eess.SP↗

arXiv2020

Viscous flow properties and hydrodynamic diameter of phenothiazine-based redox-active molecules in different supporting salt environments

We report viscous flow properties of a redox-active organic molecule, N-(2-(2-methoxyethoxy)ethyl)phenothiazine (MEEPT), a candidate for non-aqueous redox flow batteries, and two of its radical cation salts. A microfluidic viscometer enabled the use of small sample volumes in determining viscosity as a function of shear rate and concentration in the non-aqueous solvent, acetonitrile, both with and without supporting salts. All solutions tested show Newtonian behavior over shear rates of up to 30,000 1/s, which is rationalized by scaling arguments for the diffusion-based relaxation time of a single MEEPT molecule without aggregation. Neat MEEPT is flowable but with a large viscosity (412 mPa s) at room temperature), which is approximately 1,000 times larger than acetonitrile. When dissolved in acetonitrile, MEEPT solutions have low viscosities; at concentrations up to 0.5 M, the viscosity increases by less than a factor of two. From concentration-dependent viscosity measurements, molecular information is inferred from intrinsic viscosity (hydrodynamic diameter) and the Huggins coefficient (interactions). Model fit credibility is assessed using the Bayesian Information Criterion (BIC). It is found that the MEEPT and its charged cation are "flowable" and do not flocculate at concentrations up to 0.5 M. MEEPT has a hydrodynamic diameter of around 0.85 nm, which is largely insensitive to supporting salt and state of charge. This size is comparable to molecular dimensions of single molecules obtained from optimized structures using density function theory calculations. The results suggest that MEEPT is a promising candidate for redox flow batteries in terms of its viscous flow properties.

cond-mat.soft↗

arXiv2020

Varied fusion reaction probability induced by ion stopping modification in laser-driven plasma with different temperature

The dynamics of nuclear reaction in plasma is a fundamental issue in many high energy density researches, such as the astrophysical reactions and the inertial confinement fusion. The effective reaction cross-sections and ion stopping power in plasma need to be taken into account to analyze the reactivity. In this research, we have experimentally investigated the from D-D reactions from interactions between deuteron beams and deuterated polystyrene (CD) plasma, driven by two laser pulses respectively. The neutron yields, plasma density and deuteron energy loss in plasma have been measured, and the plasma temperature and deuteron stopping power have been analyzed from simulations. It is shown that, compared with a cold target, the reaction probability in plasma conditions can be enhanced or suppressed, which is ascribed to the deuteron stopping power modifications in plasma. In hotter CD plasma, the energy loss of moderate energetic deuterons reduces, which leads to higher D-D reaction probability, while the contrary happens in colder plasma. This work provides new understanding of fusion reactions in plasma environment.

physics.plasm-ph↗