arXiv subjects

Jie Chen

Publications and source records attributed to Jie Chen.

At least 613 records · Page 34Linked to original sources

arXiv2019

Large topological Hall effect in a geometrically frustrated kagome magnet Fe$_3$Sn$_2$

We report on the observation of a large topological Hall effect (THE) over a wide temperature region in a geometrically frustrated Fe3Sn2 magnet with a kagome-bilayer structure. We found that the magnitude of the THE resistivity increases with temperature and reaches -0.875 μΩ.cm at 380 K. Moreover, the critical magnetic fields with the change of THE are consistent with the magnetic structure transformation, which indicates that the real-space fictitious magnetic field is proportional to the formation of magnetic skyrmions in Fe3Sn2. The results strongly suggest that the large THE originates from the topological magnetic spin textures and may open up further research opportunities in exploring emergent phenomena in kagome materials.

cond-mat.mtrl-sci↗

arXiv2019

Online Planner Selection with Graph Neural Networks and Adaptive Scheduling

Automated planning is one of the foundational areas of AI. Since no single planner can work well for all tasks and domains, portfolio-based techniques have become increasingly popular in recent years. In particular, deep learning emerges as a promising methodology for online planner selection. Owing to the recent development of structural graph representations of planning tasks, we propose a graph neural network (GNN) approach to selecting candidate planners. GNNs are advantageous over a straightforward alternative, the convolutional neural networks, in that they are invariant to node permutations and that they incorporate node labels for better inference. Additionally, for cost-optimal planning, we propose a two-stage adaptive scheduling method to further improve the likelihood that a given task is solved in time. The scheduler may switch at halftime to a different planner, conditioned on the observed performance of the first one. Experimental results validate the effectiveness of the proposed method against strong baselines, both deep learning and non-deep learning based. The code is available at \url{https://github.com/matenure/GNN_planner}.

cs.AI↗

arXiv2019

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

Graph representation learning resurges as a trending research subject owing to the widespread use of deep learning for Euclidean data, which inspire various creative designs of neural networks in the non-Euclidean domain, particularly graphs. With the success of these graph neural networks (GNN) in the static setting, we approach further practical scenarios where the graph dynamically evolves. Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics. These methods require the knowledge of a node in the full time span (including both training and testing) and are less applicable to the frequent change of the node set. In some extreme scenarios, the node sets at different time steps may completely differ. To resolve this challenge, we propose EvolveGCN, which adapts the graph convolutional network (GCN) model along the temporal dimension without resorting to node embeddings. The proposed approach captures the dynamism of the graph sequence through using an RNN to evolve the GCN parameters. Two architectures are considered for the parameter evolution. We evaluate the proposed approach on tasks including link prediction, edge classification, and node classification. The experimental results indicate a generally higher performance of EvolveGCN compared with related approaches. The code is available at \url{https://github.com/IBM/EvolveGCN}.

cs.LG↗

arXiv2019

DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition

Self-attention networks (SAN) have been introduced into automatic speech recognition (ASR) and achieved state-of-the-art performance owing to its superior ability in capturing long term dependency. One of the key ingredients is the self-attention mechanism which can be effectively performed on the whole utterance level. In this paper, we try to investigate whether even more information beyond the whole utterance level can be exploited and beneficial. We propose to apply self-attention layer with augmented memory to ASR. Specifically, we first propose a variant model architecture which combines deep feed-forward sequential memory network (DFSMN) with self-attention layers to form a better baseline model compared with a purely self-attention network. Then, we propose and compare two kinds of additional memory structures added into self-attention layers. Experiments on large-scale LVCSR tasks show that on four individual test sets, the DFSMN-SAN architecture outperforms vanilla SAN encoder by 5% relatively in character error rate (CER). More importantly, the additional memory structure provides further 5% to 11% relative improvement in CER.

eess.AS↗

arXiv2019

Charging of quantum batteries with general harmonic power

We analyse the charging process of quantum batteries with general harmonic power. To describe the charge efficiency, we introduce the charge saturation and the charging power, and divide the charging mode into the saturated charging mode and the unsaturated charging mode. The relationships between the time-dependent charge saturation and the parameters of general driving field are discussed both analytically and numerically. And according to the Floquet theorem, we give the expressions of time-dependent charge saturation with the quasiengery and the Floquet states of the system. With both the analytical and numerical results, we find the optimal parameters to reach the best charging efficiency.

quant-ph↗

arXiv2019

Deep Learning for Generic Object Detection: A Survey

Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

cs.CV↗

arXiv2019

Attention on Attention for Image Captioning

Attention mechanisms are widely used in current encoder/decoder frameworks of image captioning, where a weighted average on encoded vectors is generated at each time step to guide the caption decoding process. However, the decoder has little idea of whether or how well the attended vector and the given attention query are related, which could make the decoder give misled results. In this paper, we propose an Attention on Attention (AoA) module, which extends the conventional attention mechanisms to determine the relevance between attention results and queries. AoA first generates an information vector and an attention gate using the attention result and the current context, then adds another attention by applying element-wise multiplication to them and finally obtains the attended information, the expected useful knowledge. We apply AoA to both the encoder and the decoder of our image captioning model, which we name as AoA Network (AoANet). Experiments show that AoANet outperforms all previously published methods and achieves a new state-of-the-art performance of 129.8 CIDEr-D score on MS COCO Karpathy offline test split and 129.6 CIDEr-D (C40) score on the official online testing server. Code is available at https://github.com/husthuaan/AoANet.

cs.CV↗

arXiv2019

Comb-mode-resolved adaptive sampling terahertz dual-comb spectroscopy with a free-running single-cavity fiber laser

Mode-resolved dual-comb spectroscopy (DCS) is an emerging spectroscopic tool with the potential to simultaneously achieve a broad spectral coverage and ultrahigh spectral resolution in terahertz (THz) spectroscopy. However, the need for two independently stabilized ultrafast lasers significantly hampers the potential application of DCS techniques. In this article, we demonstrate mode-resolved DCS in the THz region based on a free-running single-cavity dual-comb fiber laser with adaptive sampling. Low-pressure spectroscopy of acetonitrile gas with absorption features approaching the Doppler limit is demonstrated by comb-mode-resolved measurements with a spectral sampling spacing of 48.8 MHz, a spectral resolution of less than 5 MHz and a signal-to-noise ratio of ~50 dB. The successful demonstration of the proposed method clearly indicates the great potential for the realization of low-complexity, MHz-resolution THz spectroscopy instrumentation.

physics.ins-det↗

arXiv2019

Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics

Anti-money laundering (AML) regulations play a critical role in safeguarding financial systems, but bear high costs for institutions and drive financial exclusion for those on the socioeconomic and international margins. The advent of cryptocurrency has introduced an intriguing paradox: pseudonymity allows criminals to hide in plain sight, but open data gives more power to investigators and enables the crowdsourcing of forensic analysis. Meanwhile advances in learning algorithms show great promise for the AML toolkit. In this workshop tutorial, we motivate the opportunity to reconcile the cause of safety with that of financial inclusion. We contribute the Elliptic Data Set, a time series graph of over 200K Bitcoin transactions (nodes), 234K directed payment flows (edges), and 166 node features, including ones based on non-public data; to our knowledge, this is the largest labelled transaction data set publicly available in any cryptocurrency. We share results from a binary classification task predicting illicit transactions using variations of Logistic Regression (LR), Random Forest (RF), Multilayer Perceptrons (MLP), and Graph Convolutional Networks (GCN), with GCN being of special interest as an emergent new method for capturing relational information. The results show the superiority of Random Forest (RF), but also invite algorithmic work to combine the respective powers of RF and graph methods. Lastly, we consider visualization for analysis and explainability, which is difficult given the size and dynamism of real-world transaction graphs, and we offer a simple prototype capable of navigating the graph and observing model performance on illicit activity over time. With this tutorial and data set, we hope to a) invite feedback in support of our ongoing inquiry, and b) inspire others to work on this societally important challenge.

cs.SI↗

arXiv2019

Distributed Global Output-Feedback Control for a Class of Euler-Lagrange Systems

This published paper investigates the distributed tracking control problem for a class of Euler-Lagrange multi-agent systems when the agents can only measure the positions. In this case, the lack of the separation principle and the strong nonlinearity in unmeasurable states pose severe technical challenges to global output-feedback control design. To overcome these difficulties, a global nonsingular coordinate transformation matrix in the upper triangular form is firstly proposed such that the nonlinear dynamic model can be partially linearized with respect to the unmeasurable states. And, a new type of velocity observers is designed to estimate the unmeasurable velocities for each system. Then, based on the outputs of the velocity observers, we propose distributed control laws that enable the coordinated tracking control system to achieve uniform global exponential stability (UGES). Both theoretical analysis and numerical simulations are presented to validate the effectiveness of the proposed control scheme. Followed by the original paper, a typo and a mistake is corrected.

eess.SY↗

arXiv2019

Intelligent Reflecting Surface: A Programmable Wireless Environment for Physical Layer Security

In this paper, we introduce an intelligent reflecting surface (IRS) to provide a programmable wireless environment for physical layer security. By adjusting the reflecting coefficients, the IRS can change the attenuation and scattering of the incident electromagnetic wave so that it can propagate in a desired way toward the intended receiver. Specifically, we consider a downlink multiple-input single-output (MISO) broadcast system where the base station (BS) transmits independent data streams to multiple legitimate receivers and keeps them secret from multiple eavesdroppers. By jointly optimizing the beamformers at the BS and reflecting coefficients at the IRS, we formulate a minimum-secrecy-rate maximization problem under various practical constraints on the reflecting coefficients. The constraints capture the scenarios of both continuous and discrete reflecting coefficients of the reflecting elements. Due to the non-convexity of the formulated problem, we propose an efficient algorithm based on the alternating optimization and the path-following algorithm to solve it in an iterative manner. Besides, we show that the proposed algorithm can converge to a local (global) optimum. Furthermore, we develop two suboptimal algorithms with some forms of closed-form solutions to reduce the computational complexity. Finally, the simulation results validate the advantages of the introduced IRS and the effectiveness of the proposed algorithms

eess.SP↗

arXiv2019

Large Intelligent Surface/Antennas (LISA): Making Reflective Radios Smart

Large intelligent surface/antennas (LISA), a two-dimensional artificial structure with a large number of reflective-surface/antenna elements, is a promising reflective radio technology to construct programmable wireless environments in a smart way. Specifically, each element of the LISA adjusts the reflection of the incident electromagnetic waves with unnatural properties, such as negative refraction, perfect absorption, and anomalous reflection, thus the wireless environments can be software-defined according to various design objectives. In this paper, we introduce the reflective radio basics, including backscattering principles, backscatter communication, and reflective relay, and the fundamentals and implementations of LISA technology. Then, we present an overview of the state-of-the-art research on emerging applications of LISA-aided wireless networks. Finally, the limitations, challenges, and open issues associated with LISA for future wireless applications are discussed.

cs.IT↗

arXiv2019

Weighted Sum-Rate Optimization for Intelligent Reflecting Surface Enhanced Wireless Networks

Intelligent reflecting surface (IRS) is a promising solution to build a programmable wireless environment for future communication systems. In practice, an IRS consists of massive low-cost elements, which can steer the incident signal in fully customizable ways by passive beamforming. In this paper, we consider an IRS-aided multiuser multiple-input single-output (MISO) downlink communication system. In particular, the weighted sum-rate of all users is maximized by joint optimizing the active beamforming at the base-station (BS) and the passive beamforming at the IRS. In addition, we consider a practical IRS assumption, in which the passive elements can only shift the incident signal to discrete phase levels. This non-convex problem is firstly decoupled via Lagrangian dual transform, and then the active and passive beamforming can be optimized alternatingly. The active beamforming at BS is optimized based on the fractional programming method. Then, three efficient algorithms with closed-form expressions are proposed for the passive beamforming at IRS. Simulation results have verified the effectiveness of the proposed algorithms as compared to different benchmark schemes.

eess.SP↗

arXiv2019

Learning discriminative features in sequence training without requiring framewise labelled data

In this work, we try to answer two questions: Can deeply learned features with discriminative power benefit an ASR system's robustness to acoustic variability? And how to learn them without requiring framewise labelled sequence training data? As existing methods usually require knowing where the labels occur in the input sequence, they have so far been limited to many real-world sequence learning tasks. We propose a novel method which simultaneously models both the sequence discriminative training and the feature discriminative learning within a single network architecture, so that it can learn discriminative deep features in sequence training that obviates the need for presegmented training data. Our experiment in a realistic industrial ASR task shows that, without requiring any specific fine-tuning or additional complexity, our proposed models have consistently outperformed state-of-the-art models and significantly reduced Word Error Rate (WER) under all test conditions, and especially with highest improvements under unseen noise conditions, by relative 12.94%, 8.66% and 5.80%, showing our proposed models can generalize better to acoustic variability.

cs.LG↗

arXiv2019

IPC: A Benchmark Data Set for Learning with Graph-Structured Data

Benchmark data sets are an indispensable ingredient of the evaluation of graph-based machine learning methods. We release a new data set, compiled from International Planning Competitions (IPC), for benchmarking graph classification, regression, and related tasks. Apart from the graph construction (based on AI planning problems) that is interesting in its own right, the data set possesses distinctly different characteristics from popularly used benchmarks. The data set, named IPC, consists of two self-contained versions, grounded and lifted, both including graphs of large and skewedly distributed sizes, posing substantial challenges for the computation of graph models such as graph kernels and graph neural networks. The graphs in this data set are directed and the lifted version is acyclic, offering the opportunity of benchmarking specialized models for directed (acyclic) structures. Moreover, the graph generator and the labeling are computer programmed; thus, the data set may be extended easily if a larger scale is desired. The data set is accessible from \url{https://github.com/IBM/IPC-graph-data}.

cs.LG↗

arXiv2019

Distributed Solver for Discrete-Time Lyapunov Equations Over Dynamic Networks with Linear Convergence Rate

This paper investigates the problem of solving discrete-time Lyapunov equations (DTLE) over a multi-agent system, where every agent has access to its local information and communicates with its neighbors. To obtain a solution to DTLE, a distributed algorithm with uncoordinated constant step sizes is proposed over time-varying topologies. The convergence properties and the range of constant step sizes of the proposed algorithm are analyzed. Moreover, a linear convergence rate is proved and the convergence performances over dynamic networks are verified by numerical simulations.

math.OC↗

arXiv2019

Time Series Simulation by Conditional Generative Adversarial Net

Generative Adversarial Net (GAN) has been proven to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions can be both categorical and continuous variables containing different kinds of auxiliary information. Our simulation studies show that CGAN is able to learn different kinds of normal and heavy tail distributions, as well as dependent structures of different time series and it can further generate conditional predictive distributions consistent with the training data distributions. We also provide an in-depth discussion on the rationale of GAN and the neural network as hierarchical splines to draw a clear connection with the existing statistical method for distribution generation. In practice, CGAN has a wide range of applications in the market risk and counterparty risk analysis: it can be applied to learn the historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES) and predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate CGAN is able to outperform the Historic Simulation, a popular method in market risk analysis for the calculation of VaR. CGAN can also be applied in the economic time series modeling and forecasting, and an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN is given at the end of the paper.

stat.ML↗

arXiv2019

DAG-GNN: DAG Structure Learning with Graph Neural Networks

Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential in the number of graph nodes. A recent breakthrough formulates the problem as a continuous optimization with a structural constraint that ensures acyclicity (Zheng et al., 2018). The authors apply the approach to the linear structural equation model (SEM) and the least-squares loss function that are statistically well justified but nevertheless limited. Motivated by the widespread success of deep learning that is capable of capturing complex nonlinear mappings, in this work we propose a deep generative model and apply a variant of the structural constraint to learn the DAG. At the heart of the generative model is a variational autoencoder parameterized by a novel graph neural network architecture, which we coin DAG-GNN. In addition to the richer capacity, an advantage of the proposed model is that it naturally handles discrete variables as well as vector-valued ones. We demonstrate that on synthetic data sets, the proposed method learns more accurate graphs for nonlinearly generated samples; and on benchmark data sets with discrete variables, the learned graphs are reasonably close to the global optima. The code is available at \url{https://github.com/fishmoon1234/DAG-GNN}.

cs.LG↗