arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 1,315 records · Page 73Linked to original sources

arXiv2020

Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark

Since real-world objects and their interactions are often multi-modal and multi-typed, heterogeneous networks have been widely used as a more powerful, realistic, and generic superclass of traditional homogeneous networks (graphs). Meanwhile, representation learning (\aka~embedding) has recently been intensively studied and shown effective for various network mining and analytical tasks. In this work, we aim to provide a unified framework to deeply summarize and evaluate existing research on heterogeneous network embedding (HNE), which includes but goes beyond a normal survey. Since there has already been a broad body of HNE algorithms, as the first contribution of this work, we provide a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms. Moreover, existing HNE algorithms, though mostly claimed generic, are often evaluated on different datasets. Understandable due to the application favor of HNE, such indirect comparisons largely hinder the proper attribution of improved task performance towards effective data preprocessing and novel technical design, especially considering the various ways possible to construct a heterogeneous network from real-world application data. Therefore, as the second contribution, we create four benchmark datasets with various properties regarding scale, structure, attribute/label availability, and \etc.~from different sources, towards handy and fair evaluations of HNE algorithms. As the third contribution, we carefully refactor and amend the implementations and create friendly interfaces for 13 popular HNE algorithms, and provide all-around comparisons among them over multiple tasks and experimental settings.

cs.SI↗

arXiv2020

On Convergence of Gradient Expected Sarsa($λ$)

We study the convergence of $\mathtt{Expected~Sarsa}(λ)$ with linear function approximation. We show that applying the off-line estimate (multi-step bootstrapping) to $\mathtt{Expected~Sarsa}(λ)$ is unstable for off-policy learning. Furthermore, based on convex-concave saddle-point framework, we propose a convergent $\mathtt{Gradient~Expected~Sarsa}(λ)$ ($\mathtt{GES}(λ)$) algorithm. The theoretical analysis shows that our $\mathtt{GES}(λ)$ converges to the optimal solution at a linear convergence rate, which is comparable to extensive existing state-of-the-art gradient temporal difference learning algorithms. Furthermore, we develop a Lyapunov function technique to investigate how the step-size influences finite-time performance of $\mathtt{GES}(λ)$, such technique of Lyapunov function can be potentially generalized to other GTD algorithms. Finally, we conduct experiments to verify the effectiveness of our $\mathtt{GES}(λ)$.

cs.LG↗

arXiv2020

Improving EEG Decoding via Clustering-based Multi-task Feature Learning

Accurate electroencephalogram (EEG) pattern decoding for specific mental tasks is one of the key steps for the development of brain-computer interface (BCI), which is quite challenging due to the considerably low signal-to-noise ratio of EEG collected at the brain scalp. Machine learning provides a promising technique to optimize EEG patterns toward better decoding accuracy. However, existing algorithms do not effectively explore the underlying data structure capturing the true EEG sample distribution, and hence can only yield a suboptimal decoding accuracy. To uncover the intrinsic distribution structure of EEG data, we propose a clustering-based multi-task feature learning algorithm for improved EEG pattern decoding. Specifically, we perform affinity propagation-based clustering to explore the subclasses (i.e., clusters) in each of the original classes, and then assign each subclass a unique label based on a one-versus-all encoding strategy. With the encoded label matrix, we devise a novel multi-task learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses. We then train a linear support vector machine with the optimized features for EEG pattern decoding. Extensive experimental studies are conducted on three EEG datasets to validate the effectiveness of our algorithm in comparison with other state-of-the-art approaches. The improved experimental results demonstrate the outstanding superiority of our algorithm, suggesting its prominent performance for EEG pattern decoding in BCI applications.

eess.SP↗

arXiv2020

Optical Wavelength Guided Self-Supervised Feature Learning For Galaxy Cluster Richness Estimate

Most galaxies in the nearby Universe are gravitationally bound to a cluster or group of galaxies. Their optical contents, such as optical richness, are crucial for understanding the co-evolution of galaxies and large-scale structures in modern astronomy and cosmology. The determination of optical richness can be challenging. We propose a self-supervised approach for estimating optical richness from multi-band optical images. The method uses the data properties of the multi-band optical images for pre-training, which enables learning feature representations from a large but unlabeled dataset. We apply the proposed method to the Sloan Digital Sky Survey. The result shows our estimate of optical richness lowers the mean absolute error and intrinsic scatter by 11.84% and 20.78%, respectively, while reducing the need for labeled training data by up to 60%. We believe the proposed method will benefit astronomy and cosmology, where a large number of unlabeled multi-band images are available, but acquiring image labels is costly.

cs.CV↗

arXiv2020

Downfolding the Molecular Hamiltonian Matrix using Quantum Community Detection

Calculating the ground state energy of a molecule efficiently is of great interest in quantum chemistry. The exact numerical solution of the electronic Schrodinger equation remains unfeasible for most molecules requiring approximate methods at best. In this paper we introduce the use of Quantum Community Detection performed using the D-Wave quantum annealer to reduce the molecular Hamiltonian matrix without chemical knowledge. Given a molecule represented by a matrix of Slater determinants, the connectivity between Slater determinants is viewed as a graph adjacency matrix for determining multiple communities based on modularity maximization. The resulting lowest energy cluster of Slater determinants is used to calculate the ground state energy within chemical accuracy. The details of this method are described along with demonstrating its performance across multiple molecules of interest and a bond dissociation example. This approach is general and can be used as part of electronic structure calculations to reduce the computation required.

physics.chem-ph↗

arXiv2020

Effective, Efficient and Robust Neural Architecture Search

Recent advances in adversarial attacks show the vulnerability of deep neural networks searched by Neural Architecture Search (NAS). Although NAS methods can find network architectures with the state-of-the-art performance, the adversarial robustness and resource constraint are often ignored in NAS. To solve this problem, we propose an Effective, Efficient, and Robust Neural Architecture Search (E2RNAS) method to search a neural network architecture by taking the performance, robustness, and resource constraint into consideration. The objective function of the proposed E2RNAS method is formulated as a bi-level multi-objective optimization problem with the upper-level problem as a multi-objective optimization problem, which is different from existing NAS methods. To solve the proposed objective function, we integrate the multiple-gradient descent algorithm, a widely studied gradient-based multi-objective optimization algorithm, with the bi-level optimization. Experiments on benchmark datasets show that the proposed E2RNAS method can find adversarially robust architectures with optimized model size and comparable classification accuracy.

cs.LG↗

arXiv2020

Multi-Task Adversarial Attack

Deep neural networks have achieved impressive performance in various areas, but they are shown to be vulnerable to adversarial attacks. Previous works on adversarial attacks mainly focused on the single-task setting. However, in real applications, it is often desirable to attack several models for different tasks simultaneously. To this end, we propose Multi-Task adversarial Attack (MTA), a unified framework that can craft adversarial examples for multiple tasks efficiently by leveraging shared knowledge among tasks, which helps enable large-scale applications of adversarial attacks on real-world systems. More specifically, MTA uses a generator for adversarial perturbations which consists of a shared encoder for all tasks and multiple task-specific decoders. Thanks to the shared encoder, MTA reduces the storage cost and speeds up the inference when attacking multiple tasks simultaneously. Moreover, the proposed framework can be used to generate per-instance and universal perturbations for targeted and non-targeted attacks. Experimental results on the Office-31 and NYUv2 datasets demonstrate that MTA can improve the quality of attacks when compared with its single-task counterpart.

cs.LG↗

arXiv2020

Domain Concretization from Examples: Addressing Missing Domain Knowledge via Robust Planning

The assumption of complete domain knowledge is not warranted for robot planning and decision-making in the real world. It could be due to design flaws or arise from domain ramifications or qualifications. In such cases, existing planning and learning algorithms could produce highly undesirable behaviors. This problem is more challenging than partial observability in the sense that the agent is unaware of certain knowledge, in contrast to it being partially observable: the difference between known unknowns and unknown unknowns. In this work, we formulate it as the problem of Domain Concretization, an inverse problem to domain abstraction. Based on an incomplete domain model provided by the designer and teacher traces from human users, our algorithm searches for a candidate model set under a minimalistic model assumption. It then generates a robust plan with the maximum probability of success under the set of candidate models. In addition to a standard search formulation in the model-space, we propose a sample-based search method and also an online version of it to improve search time. We tested our approach on IPC domains and a simulated robotics domain where incompleteness was introduced by removing domain features from the complete model. Results show that our planning algorithm increases the plan success rate without impacting the cost much.

cs.AI↗

arXiv2020

Barycode-based GJK Algorithm

In this paper, we present a more efficient GJK algorithm to solve the collision detection and distance query problems in 2D. We contribute in two aspects: First, we propose a new barycode-based sub-distance algorithm that does not only provide a simple and unified condition to determine the minimum simplex but also improve the efficiency in distant, touching, and overlap cases in distance query. Second, we provide a highly efficient implementation subroutine for collision detection by optimizing the exit conditions of our GJK distance algorithm, which shows dramatic improvements in run-time for applications that only need binary results. We benchmark our methods along with that of the well-known open-source collision detection libraries, such as Bullet, FCL, OpenGJK, Box2D, and Apollo over a range of random datasets. The results indicate that our methods and implementations outperform the state-of-the-art in both collision detection and distance query.

cs.RO↗

arXiv2020

Pseudospin-mediated Atomic-scale Vortices and Their Quantum Interferences in Monolayer Graphene

Vortex is a universal and significant phenomenon that has been known for centuries. However, creating vortices to the atomic limit has remained elusive because that the characteristic length to support a vortex is usually much larger than the atomic scale. Very recently, it was demonstrated that intervalley scattering induced by the single carbon defect of graphene leads to phase winding over a closed path surrounding the defect. Motivated by this, we demonstrate, in this Letter, that the single carbon defects at A and B sublattices of graphene can be regarded as pseudospin-mediated atomic-scale vortices with angular momenta l = +2 and -2, respectively. The quantum interferences measurements of the interacting vortices indicate that the vortices cancel each other, resulting in zero total angular momentum, in the |A| = |B| case, and they show aggregate chirality and angular momenta similar to a single vortex of the majority in the |A| not equal to |B| case, where |A| (|B|) is the number of vortices with angular momenta l = +2 (l = -2).

cond-mat.mtrl-sci↗

arXiv2020

Hot carrier-assisted switching of the electron-phonon interaction in 1$T$-VSe$_2$

We apply an intense infrared laser pulse in order to perturb the electronic and vibrational states in the three-dimensional charge density wave material 1$T$-VSe$_2$. Ultrafast snapshots of the light-induced hot carrier dynamics and non-equilibrium quasiparticle spectral function are collected using time- and angle-resolved photoemission spectroscopy. The hot carrier temperature and time-dependent electronic self-energy are extracted from the time-dependent spectral function, revealing that incoherent electron-phonon interactions heat the lattice above the charge density wave critical temperature on a timescale of $(200 \pm 40)$~fs. Density functional perturbation theory calculations establish that the presence of hot carriers alters the overall phonon dispersion and quenches efficient low-energy acoustic phonon scattering channels, which results in a new quasi-equilibrium state that is experimentally observed.

cond-mat.mtrl-sci↗

arXiv2020

Large-scale multilingual audio visual dubbing

We describe a system for large-scale audiovisual translation and dubbing, which translates videos from one language to another. The source language's speech content is transcribed to text, translated, and automatically synthesized into target language speech using the original speaker's voice. The visual content is translated by synthesizing lip movements for the speaker to match the translated audio, creating a seamless audiovisual experience in the target language. The audio and visual translation subsystems each contain a large-scale generic synthesis model trained on thousands of hours of data in the corresponding domain. These generic models are fine-tuned to a specific speaker before translation, either using an auxiliary corpus of data from the target speaker, or using the video to be translated itself as the input to the fine-tuning process. This report gives an architectural overview of the full system, as well as an in-depth discussion of the video dubbing component. The role of the audio and text components in relation to the full system is outlined, but their design is not discussed in detail. Translated and dubbed demo videos generated using our system can be viewed at https://www.youtube.com/playlist?list=PLSi232j2ZA6_1Exhof5vndzyfbxAhhEs5

cs.CV↗

arXiv2020

Fault Detection for Covered Conductors With High-Frequency Voltage Signals: From Local Patterns to Global Features

The detection and characterization of partial discharge (PD) are crucial for the insulation diagnosis of overhead lines with covered conductors. With the release of a large dataset containing thousands of naturally obtained high-frequency voltage signals, data-driven analysis of fault-related PD patterns on an unprecedented scale becomes viable. The high diversity of PD patterns and background noise interferences motivates us to design an innovative pulse shape characterization method based on clustering techniques, which can dynamically identify a set of representative PD-related pulses. Capitalizing on those pulses as referential patterns, we construct insightful features and develop a novel machine learning model with a superior detection performance for early-stage covered conductor faults. The presented model outperforms the winning model in a Kaggle competition and provides the state-of-the-art solution to detect real-time disturbances in the field.

eess.SP↗

arXiv2020

Improved Noisy Student Training for Automatic Speech Recognition

Recently, a semi-supervised learning method known as "noisy student training" has been shown to improve image classification performance of deep networks significantly. Noisy student training is an iterative self-training method that leverages augmentation to improve network performance. In this work, we adapt and improve noisy student training for automatic speech recognition, employing (adaptive) SpecAugment as the augmentation method. We find effective methods to filter, balance and augment the data generated in between self-training iterations. By doing so, we are able to obtain word error rates (WERs) 4.2%/8.6% on the clean/noisy LibriSpeech test sets by only using the clean 100h subset of LibriSpeech as the supervised set and the rest (860h) as the unlabeled set. Furthermore, we are able to achieve WERs 1.7%/3.4% on the clean/noisy LibriSpeech test sets by using the unlab-60k subset of LibriLight as the unlabeled set for LibriSpeech 960h. We are thus able to improve upon the previous state-of-the-art clean/noisy test WERs achieved on LibriSpeech 100h (4.74%/12.20%) and LibriSpeech (1.9%/4.1%).

eess.AS↗

arXiv2020

Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition

For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence scores can be reliably obtained from word posteriors in decoding lattices. However, for an ASR system with an auto-regressive decoder, such as an attention-based sequence-to-sequence model, computing word posteriors is difficult. An obvious alternative is to use the decoder softmax probability as the model confidence. In this paper, we first examine how some commonly used regularisation methods influence the softmax-based confidence scores and study the overconfident behaviour of end-to-end models. Then we propose a lightweight and effective approach named confidence estimation module (CEM) on top of an existing end-to-end ASR model. Experiments on LibriSpeech show that CEM can mitigate the overconfidence problem and can produce more reliable confidence scores with and without shallow fusion of a language model. Further analysis shows that CEM generalises well to speech from a moderately mismatched domain and can potentially improve downstream tasks such as semi-supervised learning.

eess.AS↗

arXiv2020

Parallel Tacotron: Non-Autoregressive and Controllable TTS

Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented with a variational autoencoder-based residual encoder. This model, called \emph{Parallel Tacotron}, is highly parallelizable during both training and inference, allowing efficient synthesis on modern parallel hardware. The use of the variational autoencoder relaxes the one-to-many mapping nature of the text-to-speech problem and improves naturalness. To further improve the naturalness, we use lightweight convolutions, which can efficiently capture local contexts, and introduce an iterative spectrogram loss inspired by iterative refinement. Experimental results show that Parallel Tacotron matches a strong autoregressive baseline in subjective evaluations with significantly decreased inference time.

cs.SD↗

arXiv2020

A Survey on Deep Learning-based Non-Invasive Brain Signals:Recent Advances and New Frontiers

Brain-Computer Interface (BCI) bridges the human's neural world and the outer physical world by decoding individuals' brain signals into commands recognizable by computer devices. Deep learning has lifted the performance of brain-computer interface systems significantly in recent years. In this article, we systematically investigate brain signal types for BCI and related deep learning concepts for brain signal analysis. We then present a comprehensive survey of deep learning techniques used for BCI, by summarizing over 230 contributions most published in the past five years. Finally, we discuss the applied areas, opening challenges, and future directions for deep learning-based BCI.

cs.HC↗

arXiv2020

Order Matters: Generating Progressive Explanations for Planning Tasks in Human-Robot Teaming

Prior work on generating explanations in a planning and decision-making context has focused on providing the rationale behind an AI agent's decision making. While these methods provide the right explanations from the explainer's perspective, they fail to heed the cognitive requirement of understanding an explanation from the explainee's (the human's) perspective. In this work, we set out to address this issue by first considering the influence of information order in an explanation, or the progressiveness of explanations. Intuitively, progression builds later concepts on previous ones and is known to contribute to better learning. In this work, we aim to investigate similar effects during explanation generation when an explanation is broken into multiple parts that are communicated sequentially. The challenge here lies in modeling the humans' preferences for information order in receiving such explanations to assist understanding. Given this sequential process, a formulation based on goal-based MDP for generating progressive explanations is presented. The reward function of this MDP is learned via inverse reinforcement learning based on explanations that are retrieved via human subject studies. We first evaluated our approach on a scavenger-hunt domain to demonstrate its effectively in capturing the humans' preferences. Upon analyzing the results, it revealed something more fundamental: the preferences arise strongly from both domain dependent and independence features. The correlation with domain independent features pushed us to verify this result further in an escape room domain. Results confirmed our hypothesis that the process of understanding an explanation was a dynamic process. The human preference that reflected this aspect corresponded exactly to the progression for knowledge assimilation hidden deeper in our cognitive process.

cs.AI↗