In recent years, there have been an increasing number of applications of tensor completion based on the tensor train (TT) format because of its efficiency and effectiveness in dealing with higher-order tensor data. However, existing tensor completion
methods using TT decomposition have two obvious drawbacks. One is that they only consider mode weights according to the degree of mode balance, even though some elements are recovered better in an unbalanced mode. The other is that serious blocking artifacts appear when the missing element rate is relatively large. To remedy such two issues, in this work, we propose a novel tensor completion approach via the element-wise weighted technique. Accordingly, a novel formulation for tensor completion and an efficient optimization algorithm, called as tensor completion by parallel weighted matrix factorization via tensor train (TWMac-TT), is proposed. In addition, we specifically consider the recovery quality of edge elements from adjacent blocks. Different from traditional reshaping and ket augmentation, we utilize a new tensor augmentation technique called overlapping ket augmentation, which can further avoid blocking artifacts. We then conduct extensive performance evaluations on synthetic data and several real image data sets. Our experimental results demonstrate that the proposed algorithm TWMac-TT outperforms several other competing tensor completion methods.
The oscillation of Majorana modes with near zero energy plays a very important role for ascertaining Majorana fermions. The edge states, which also have almost-zero-energy in one-dimensional Su-Schrieffer-Heeger chain (SSHc), have been extensively st
udied for their topologically protected properties when the on-sites have dissipations induced by independent environments. We here show that common environments shared by each pair of the nearest neighbour sites in the SSHc can result in dissipative couplings between sites, and thus change topologically trivial phase to nontrivial one. The Majorana-like oscillation for the finite-size hybridizations of two non-Hermitian edge states with complex localization lengths can be induced by the dissipative coupling. The controllable topology parameter of the SSHc plays the role of the magnetic field in the nanowire for controlling Majorana oscillation. The measurement for the oscillation is proposed. Our study provides a new way to manipulate edge states and is experimentally feasible within current technology of superconducting quantum circuits.
In the past years, significant improvements in the field of neural architecture search(NAS) have been made. However, it is still challenging to search for efficient networks due to the gap between the searched constraint and real inference time exist
s. To search for a high-performance network with low inference time, several previous works set a computational complexity constraint for the search algorithm. However, many factors affect the speed of inference(e.g., FLOPs, MACs). The correlation between a single indicator and the latency is not strong. Currently, some re-parameterization(Rep) techniques are proposed to convert multi-branch to single-path architecture which is inference-friendly. Nevertheless, multi-branch architectures are still human-defined and inefficient. In this work, we propose a new search space that is suitable for structural re-parameterization techniques. RepNAS, a one-stage NAS approach, is present to efficiently search the optimal diverse branch block(ODBB) for each layer under the branch number constraint. Our experimental results show the searched ODBB can easily surpass the manual diverse branch block(DBB) with efficient training. Code and models will be available sooner.
As a potential technology feature for 6G wireless networks, the idea of sensing-communication integration requires the system not only to complete reliable multi-user communication but also to achieve accurate environment sensing. In this paper, we c
onsider such a joint communication and sensing (JCAS) scenario, in which multiple users use the sparse code multiple access (SCMA) scheme to communicate with the wireless access point (AP). Part of the user signals are scattered by the environment object and reflected by an intelligent reflective surface (IRS) before they arrive at the AP. We exploit the sparsity of both the structured user signals and the unstructured environment and propose an iterative and incremental joint multi-user communication and environment sensing scheme, in which the two processes, i.e., multi-user information detection and environment object detection, interweave with each other thanks to their intrinsic mutual dependence. The proposed algorithm is sliding-window based and also graph based, which can keep on sensing the environment as long as there are illuminating user signals. The trade-off relationship between the key system parameters is analyzed, and the simulation result validates the convergence and effectiveness of the proposed algorithm.
This paper investigates a joint beamforming design in a multiuser multiple-input single-output (MISO) communication network aided with an intelligent reflecting surface (IRS) panel. The symbol-level precoding (SLP) is adopted to enhance the system pe
rformance by exploiting the multiuser interference (MUI) with consideration of bounded channel uncertainty. The joint beamforming design is formulated into a nonconvex worst-case robust programming to minimize the transmit power subject to single-to-noise ratio (SNR) requirements. To address the challenges due to the constant modulus and the coupling of the beamformers, we first study the single-user case. Specifically, we propose and compare two algorithms based on the semidefinite relaxation (SDR) and alternating optimization (AO) methods, respectively. It turns out that the AO-based algorithm has much lower computational complexity but with almost the same power to the SDR-based algorithm. Then, we apply the AO technique to the multiuser case and thereby develop an algorithm based on the proximal gradient descent (PGD) method. The algorithm can be generalized to the case of finite-resolution IRS and the scenario with direct links from the transmitter to the users. Numerical results show that the SLP can significantly improve the system performance. Meanwhile, 3-bit phase shifters can achieve near-optimal power performance.
This work introduces a tensor-based framework of graph signal processing over multilayer networks (M-GSP) to analyze high-dimensional signal interactions. Following Part Is introduction of fundamental definitions and spectrum properties of M-GSP, thi
s second Part focuses on more detailed discussions of implementation and applications of M-GSP. Specifically, we define the concepts of stationary process, convolution, bandlimited signals, and sampling theory over multilayer networks. We also develop fundamentals of filter design and derive approximated methods of spectrum estimation within the proposed framework. For practical applications, we further present several MLN-based methods for signal processing and data analysis. Our experimental results demonstrate significant performance improvement using our M-GSP framework over traditional signal processing solutions.
Signal processing over single-layer graphs has become a mainstream tool owing to its power in revealing obscure underlying structures within data signals. For generally, many real-life datasets and systems are characterized by more complex interactio
ns among distinct entities. Such complex interactions may represent multiple levels of interactions that are difficult to be modeled with a single layer graph and can instead be captured by multiple layers of graph connections. Such multilayer/multi-level data structure can be more naturally modeled and captured by a high-dimensional multi-layer network (MLN). This work generalizes traditional graph signal processing (GSP) over multilayer networks for analysis of such multilayer signal features and their interactions. We propose a tensor-based framework of this multilayer network signal processing (M-GSP) in this two-part series. Specially, Part I introduces the fundamentals of M-GSP and studies spectrum properties of MLN Fourier space. We further describe its connections to traditional digital signal processing and GSP. Part II focuses on several major tools within the M-GSP framework for signal processing and data analysis. We provide results to demonstrate the efficacy and benefits of applying multilayer networks and the M-GSP in practical scenarios.
Recent works on implicit neural representations have shown promising results for multi-view surface reconstruction. However, most approaches are limited to relatively simple geometries and usually require clean object masks for reconstructing complex
and concave objects. In this work, we introduce a novel neural surface reconstruction framework that leverages the knowledge of stereo matching and feature consistency to optimize the implicit surface representation. More specifically, we apply a signed distance field (SDF) and a surface light field to represent the scene geometry and appearance respectively. The SDF is directly supervised by geometry from stereo matching, and is refined by optimizing the multi-view feature consistency and the fidelity of rendered images. Our method is able to improve the robustness of geometry estimation and support reconstruction of complex scene topologies. Extensive experiments have been conducted on DTU, EPFL and Tanks and Temples datasets. Compared to previous state-of-the-art methods, our method achieves better mesh reconstruction in wide open scenes without masks as input.
Text normalization (TN) and inverse text normalization (ITN) are essential preprocessing and postprocessing steps for text-to-speech synthesis and automatic speech recognition, respectively. Many methods have been proposed for either TN or ITN, rangi
ng from weighted finite-state transducers to neural networks. Despite their impressive performance, these methods aim to tackle only one of the two tasks but not both. As a result, in a complete spoken dialog system, two separate models for TN and ITN need to be built. This heterogeneity increases the technical complexity of the system, which in turn increases the cost of maintenance in a production setting. Motivated by this observation, we propose a unified framework for building a single neural duplex system that can simultaneously handle TN and ITN. Combined with a simple but effective data augmentation method, our systems achieve state-of-the-art results on the Google TN dataset for English and Russian. They can also reach over 95% sentence-level accuracy on an internal English TN dataset without any additional fine-tuning. In addition, we also create a cleaned dataset from the Spoken Wikipedia Corpora for German and report the performance of our systems on the dataset. Overall, experimental results demonstrate the proposed duplex text normalization framework is highly effective and applicable to a range of domains and languages
There has been a growing interest in developing machine learning (ML) models for code learning tasks, e.g., comment generation and method naming. Despite substantial increase in the effectiveness of ML models, the evaluation methodologies, i.e., the
way people split datasets into training, validation, and testing sets, were not well designed. Specifically, no prior work on the aforementioned topics considered the timestamps of code and comments during evaluation (e.g., examples in the testing set might be from 2010 and examples from the training set might be from 2020). This may lead to evaluations that are inconsistent with the intended use cases of the ML models. In this paper, we formalize a novel time-segmented evaluation methodology, as well as the two methodologies commonly used in the literature: mixed-project and cross-project. We argue that time-segmented methodology is the most realistic. We also describe various use cases of ML models and provide a guideline for using methodologies to evaluate each use case. To assess the impact of methodologies, we collect a dataset of code-comment pairs with timestamps to train and evaluate several recent code learning ML models for the comment generation and method naming tasks. Our results show that different methodologies can lead to conflicting and inconsistent results. We invite the community to adopt the time-segmented evaluation methodology.
