arXiv subjects

Liang Wang

Publications and source records attributed to Liang Wang.

At least 541 records · Page 30Linked to original sources

arXiv2020

Unfolding the Alternating Optimization for Blind Super Resolution

Previous methods decompose blind super resolution (SR) problem into two sequential steps: \textit{i}) estimating blur kernel from given low-resolution (LR) image and \textit{ii}) restoring SR image based on estimated kernel. This two-step solution involves two independently trained models, which may not be well compatible with each other. Small estimation error of the first step could cause severe performance drop of the second one. While on the other hand, the first step can only utilize limited information from LR image, which makes it difficult to predict highly accurate blur kernel. Towards these issues, instead of considering these two steps separately, we adopt an alternating optimization algorithm, which can estimate blur kernel and restore SR image in a single model. Specifically, we design two convolutional neural modules, namely \textit{Restorer} and \textit{Estimator}. \textit{Restorer} restores SR image based on predicted kernel, and \textit{Estimator} estimates blur kernel with the help of restored SR image. We alternate these two modules repeatedly and unfold this process to form an end-to-end trainable network. In this way, \textit{Estimator} utilizes information from both LR and SR images, which makes the estimation of blur kernel easier. More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}. Extensive experiments on synthetic datasets and real-world images show that our model can largely outperform state-of-the-art methods and produce more visually favorable results at much higher speed. The source code is available at https://github.com/greatlog/DAN.git.

cs.CV↗

arXiv2020

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

We present JueWu-SL, the first supervised-learning-based artificial intelligence (AI) program that achieves human-level performance in playing multiplayer online battle arena (MOBA) games. Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner. Tested on Honor of Kings, the most popular MOBA at present, our AI performs competitively at the level of High King players in standard 5v5 games.

cs.AI↗

arXiv2020

Heterogeneous Graph Collaborative Filtering

Graph-based collaborative filtering (CF) algorithms have gained increasing attention. Existing work in this literature usually models the user-item interactions as a bipartite graph, where users and items are two isolated node sets and edges between them indicate their interactions. Then, the unobserved preference of users can be exploited by modeling high-order connectivity on the bipartite graph. In this work, we propose to model user-item interactions as a heterogeneous graph which consists of not only user-item edges indicating their interaction but also user-user edges indicating their similarity. We develop heterogeneous graph collaborative filtering (HGCF), a GCN-based framework which can explicitly capture both the interaction signal and similarity signal through embedding propagation on the heterogeneous graph. Since the heterogeneous graph is more connected than the bipartite graph, the sparsity issue can be alleviated and the demand for expensive high-order connectivity modeling can be lowered. Extensive experiments conducted on three public benchmarks demonstrate its superiority over the state-of-the-arts. Further analysis verifies the importance of user-user edges in the graph, justifying the rationality and effectiveness of HGCF.

cs.IR↗

arXiv2020

Transfer learning of chaotic systems

Can a neural network trained by the time series of system A be used to predict the evolution of system B? This problem, knowing as transfer learning in a broad sense, is of great importance in machine learning and data mining, yet has not been addressed for chaotic systems. Here we investigate transfer learning of chaotic systems from the perspective of synchronization-based state inference, in which a reservoir computer trained by chaotic system A is used to infer the unmeasured variables of chaotic system B, while A is different from B in either parameter or dynamics. It is found that if systems A and B are different in parameter, the reservoir computer can be well synchronized to system B. However, if systems A and B are different in dynamics, the reservoir computer fails to synchronize with system B in general. Knowledge transfer along a chain of coupled reservoir computers is also studied, and it is found that, although the reservoir computers are trained by different systems, the unmeasured variables of the driving system can be successfully inferred by the remote reservoir computer. Finally, by an experiment of chaotic pendulum, we show that the knowledge learned from the modeling system can be used to predict the evolution of the experimental system.

cs.NE↗

arXiv2020

Guarding Serverless Applications with SecLambda

As an emerging application paradigm, serverless computing attracts attention from more and more attackers. Unfortunately, security tools for conventional applications cannot be easily ported to serverless, and existing serverless security solutions are inadequate. In this paper, we present \emph{SecLambda}, an extensible security framework that leverages local function state and global application state to perform sophisticated security tasks to protect an application. We show how SecLambda can be used to achieve control flow integrity, credential protection, and rate limiting in serverless applications. We evaluate the performance overhead and security of SecLambda using realistic open-source applications, and our results suggest that SecLambda can mitigate several attacks while introducing relatively low performance overhead.

cs.CR↗

arXiv2020

Merchant Category Identification Using Credit Card Transactions

Digital payment volume has proliferated in recent years with the rapid growth of small businesses and online shops. When processing these digital transactions, recognizing each merchant's real identity (i.e., business type) is vital to ensure the integrity of payment processing systems. Conventionally, this problem is formulated as a time series classification problem solely using the merchant transaction history. However, with the large scale of the data, and changing behaviors of merchants and consumers over time, it is extremely challenging to achieve satisfying performance from off-the-shelf classification methods. In this work, we approach this problem from a multi-modal learning perspective, where we use not only the merchant time series data but also the information of merchant-merchant relationship (i.e., affinity) to verify the self-reported business type (i.e., merchant category) of a given merchant. Specifically, we design two individual encoders, where one is responsible for encoding temporal information and the other is responsible for affinity information, and a mechanism to fuse the outputs of the two encoders to accomplish the identification task. Our experiments on real-world credit card transaction data between 71,668 merchants and 433,772,755 customers have demonstrated the effectiveness and efficiency of the proposed model.

cs.LG↗

arXiv2020

GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction

Graph representation learning is of paramount importance for a variety of graph analytical tasks, ranging from node classification to community detection. Recently, graph convolutional networks (GCNs) have been successfully applied for graph representation learning. These GCNs generate node representation by aggregating features from the neighborhoods, which follows the "neighborhood aggregation" scheme. In spite of having achieved promising performance on various tasks, existing GCN-based models have difficulty in well capturing complicated non-linearity of graph data. In this paper, we first theoretically prove that coefficients of the neighborhood interacting terms are relatively small in current models, which explains why GCNs barely outperforms linear models. Then, in order to better capture the complicated non-linearity of graph data, we present a novel GraphAIR framework which models the neighborhood interaction in addition to neighborhood aggregation. Comprehensive experiments conducted on benchmark tasks including node classification and link prediction using public datasets demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2020

In and around Abelian anyon models

Anyon models are algebraic structures that model universal topological properties in topological phases of matter and can be regarded as mathematical characterization of topological order in two spacial dimensions. It is conjectured that every anyon model, or mathematically unitary modular tensor category, can be realized as the representation category of some chiral conformal field theory, or mathematically vertex operator algebra/local conformal net. This conjecture is known to be true for abelian anyon models providing support for the conjecture. We reexamine abelian anyon models from several different angles. First anyon models are algebraic data for both topological quantum field theories and chiral conformal field theories. While it is known that each abelian anyon model can be realized by a quantum abelian Chern-Simons theory and chiral conformal field theory, the construction is not algorithmic. Our goal is to provide such an explicit algorithm for a $K$-matrix in Chern-Simons theory and a positive definite even one for a lattice conformal field theory. Secondly anyon models and chiral conformal field theories underlie the bulk-edge correspondence for topological phases of matter. But there are interesting subtleties in this correspondence when stability of the edge theory and topological symmetry are taken into consideration. Therefore, our focus is on the algorithmic reconstruction of extremal chiral conformal field theories with small central charges. Finally we conjecture that a much stronger reconstruction holds for abelian anyon models: every abelian anyon model can be realized as the representation category of some non-lattice extremal vertex operator algebra generalizing the moonshine realization of the trivial anyon model.

math.QA↗

arXiv2020

Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition

One essential problem in skeleton-based action recognition is how to extract discriminative features over all skeleton joints. However, the complexity of the State-Of-The-Art (SOTA) models of this task tends to be exceedingly sophisticated and over-parameterized, where the low efficiency in model training and inference has obstructed the development in the field, especially for large-scale action datasets. In this work, we propose an efficient but strong baseline based on Graph Convolutional Network (GCN), where three main improvements are aggregated, i.e., early fused Multiple Input Branches (MIB), Residual GCN (ResGCN) with bottleneck structure and Part-wise Attention (PartAtt) block. Firstly, an MIB is designed to enrich informative skeleton features and remain compact representations at an early fusion stage. Then, inspired by the success of the ResNet architecture in Convolutional Neural Network (CNN), a ResGCN module is introduced in GCN to alleviate computational costs and reduce learning difficulties in model training while maintain the model accuracy. Finally, a PartAtt block is proposed to discover the most essential body parts over a whole action sequence and obtain more explainable representations for different skeleton action sequences. Extensive experiments on two large-scale datasets, i.e., NTU RGB+D 60 and 120, validate that the proposed baseline slightly outperforms other SOTA models and meanwhile requires much fewer parameters during training and inference procedures, e.g., at most 34 times less than DGNN, which is one of the best SOTA methods.

cs.CV↗

arXiv2020

Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems

Automatic math word problem solving has attracted growing attention in recent years. The evaluation datasets used by previous works have serious limitations in terms of scale and diversity. In this paper, we release a new large-scale and template-rich math word problem dataset named Ape210K. It consists of 210K Chinese elementary school-level math problems, which is 9 times the size of the largest public dataset Math23K. Each problem contains both the gold answer and the equations needed to derive the answer. Ape210K is also of greater diversity with 56K templates, which is 25 times more than Math23K. Our analysis shows that solving Ape210K requires not only natural language understanding but also commonsense knowledge. We expect Ape210K to be a benchmark for math word problem solving systems. Experiments indicate that state-of-the-art models on the Math23K dataset perform poorly on Ape210K. We propose a copy-augmented and feature-enriched sequence to sequence (seq2seq) model, which outperforms existing models by 3.2% on the Math23K dataset and serves as a strong baseline of the Ape210K dataset. The gap is still significant between human and our baseline model, calling for further research efforts. We make Ape210K dataset publicly available at https://github.com/yuantiku/ape210k

cs.CL↗

arXiv2020

Spatial distributions of Balmer series emissions in divertor plasmas with tungsten targets in different magnetic configurations on the EAST superconducting tokamak

The characteristics of wall recycling with different divertor configurations were investigated in this study, focusing on the observations of the spatial distributions of deuterium atomic emissions in the Balmer series (D_α, D_β, D_γ, and D_δ) with different magnetic field configurations in the Experimental Advanced Superconducting Tokamak. The observed D_α and D_β emissions were primarily relatively close to the divertor targets, while the D_γ and D_δ emissions were primarily relatively close to the X-point. The distributions of the emissions close to the divertor targets and X-point changed differently depending on the divertor configuration. These experimental results indicate that the linear comparison of parameters based on an assumption of similarity of profile shapes in different configurations is insufficient for understanding particle recycling in divertor plasmas. This is because the shape of the density profile of the recycled deuterium atoms and/or the electron density and temperature may change when the magnetic configuration is altered.

physics.plasm-ph↗

arXiv2020

Multi-Agent Deep Reinforcement Learning Based Trajectory Planning for Multi-UAV Assisted Mobile Edge Computing

An unmanned aerial vehicle (UAV)-aided mobile edge computing (MEC) framework is proposed, where several UAVs having different trajectories fly over the target area and support the user equipments (UEs) on the ground. We aim to jointly optimize the geographical fairness among all the UEs, the fairness of each UAV' UE-load and the overall energy consumption of UEs. The above optimization problem includes both integer and continues variables and it is challenging to solve. To address the above problem, a multi-agent deep reinforcement learning based trajectory control algorithm is proposed for managing the trajectory of each UAV independently, where the popular Multi-Agent Deep Deterministic Policy Gradient (MADDPG) method is applied. Given the UAVs' trajectories, a low-complexity approach is introduced for optimizing the offloading decisions of UEs. We show that our proposed solution has considerable performance over other traditional algorithms, both in terms of the fairness for serving UEs, fairness of UE-load at each UAV and energy consumption for all the UEs.

eess.SP↗

arXiv2020

Ground state cooling of magnomechanical resonator in PT-symmetric cavity magnomechanical system at room temperature

We propose to realize the ground state cooling of magnomechanical resonator in a parity-time (PT)-symmetric cavity magnomechanical system composed of a loss ferromagnetic sphere and a gain microwave cavity. In the scheme, the magnomechanical resonator can be cooled close to its ground state via the magnomechanical interaction, and it is found that the cooling effect in PT-symmetric system is much higher than that in non-PT-symmetric system. Resorting to the magnetic force noise spectrum, we investigate the final mean phonon number with experimentally feasible parameters and find surprisingly that the ground state cooling of magnomechanical resonator can be directly achieved at room temperature. Furthermore, we also illustrate that the ground state cooling can be flexibly controlled via the external magnetic field.

quant-ph↗

arXiv2020

Tasks Integrated Networks: Joint Detection and Retrieval for Image Search

The traditional object retrieval task aims to learn a discriminative feature representation with intra-similarity and inter-dissimilarity, which supposes that the objects in an image are manually or automatically pre-cropped exactly. However, in many real-world searching scenarios (e.g., video surveillance), the objects (e.g., persons, vehicles, etc.) are seldom accurately detected or annotated. Therefore, object-level retrieval becomes intractable without bounding-box annotation, which leads to a new but challenging topic, i.e. image-level search. In this paper, to address the image search issue, we first introduce an end-to-end Integrated Net (I-Net), which has three merits: 1) A Siamese architecture and an on-line pairing strategy for similar and dissimilar objects in the given images are designed. 2) A novel on-line pairing (OLP) loss is introduced with a dynamic feature dictionary, which alleviates the multi-task training stagnation problem, by automatically generating a number of negative pairs to restrict the positives. 3) A hard example priority (HEP) based softmax loss is proposed to improve the robustness of classification task by selecting hard categories. With the philosophy of divide and conquer, we further propose an improved I-Net, called DC-I-Net, which makes two new contributions: 1) two modules are tailored to handle different tasks separately in the integrated framework, such that the task specification is guaranteed. 2) A class-center guided HEP loss (C2HEP) by exploiting the stored class centers is proposed, such that the intra-similarity and inter-dissimilarity can be captured for ultimate retrieval. Extensive experiments on famous image-level search oriented benchmark datasets demonstrate that the proposed DC-I-Net outperforms the state-of-the-art tasks-integrated and tasks-separated image search models.

cs.CV↗

arXiv2020

CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning

Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous graph neural networks (GNN) require a large number of labeled nodes, which may not be accessible in real-world graph data. In this paper, we present a novel cluster-aware graph neural network (CAGNN) model for unsupervised graph representation learning using self-supervised techniques. In CAGNN, we perform clustering on the node embeddings and update the model parameters by predicting the cluster assignments. Moreover, we observe that graphs often contain inter-class edges, which mislead the GNN model to aggregate noisy information from neighborhood nodes. We further refine the graph topology by strengthening intra-class edges and reducing node connections between different classes based on cluster labels, which better preserves cluster structures in the embedding space. We conduct comprehensive experiments on two benchmark tasks using real-world datasets. The results demonstrate the superior performance of the proposed model over existing baseline methods. Notably, our model gains over 7% improvements in terms of accuracy on node clustering over state-of-the-arts.

cs.LG↗

arXiv2020

Recurrent Deconvolutional Generative Adversarial Networks with Application to Text Guided Video Generation

This paper proposes a novel model for video generation and especially makes the attempt to deal with the problem of video generation from text descriptions, i.e., synthesizing realistic videos conditioned on given texts. Existing video generation methods cannot be easily adapted to handle this task well, due to the frame discontinuity issue and their text-free generation schemes. To address these problems, we propose a recurrent deconvolutional generative adversarial network (RD-GAN), which includes a recurrent deconvolutional network (RDN) as the generator and a 3D convolutional neural network (3D-CNN) as the discriminator. The RDN is a deconvolutional version of conventional recurrent neural network, which can well model the long-range temporal dependency of generated video frames and make good use of conditional information. The proposed model can be jointly trained by pushing the RDN to generate realistic videos so that the 3D-CNN cannot distinguish them from real ones. We apply the proposed RD-GAN to a series of tasks including conventional video generation, conditional video generation, video prediction and video classification, and demonstrate its effectiveness by achieving well performance.

cs.CV↗

arXiv2020

Magnon blockade in a PT-symmetric-like cavity magnomechanical system

We investigate the magnon blockade effect in a parity-time (PT) symmetric-like three-mode cavity magnomechanical system involving the magnon-photon and magnon-phonon interactions. In the broken and unbroken PT-symmetric regions, we respectively calculate the second-order correlation function analytically and numerically and further determine the optimal value of detuning. By adjusting different system parameters, we study the different blockade mechanisms and find that the perfect magnon blockade effect can be observed under the weak parameter mechanism. Our work paves a way to achieve the magnon blockade in experiment.

quant-ph↗

arXiv2020

Multi-stream RNN for Merchant Transaction Prediction

Recently, digital payment systems have significantly changed people's lifestyles. New challenges have surfaced in monitoring and guaranteeing the integrity of payment processing systems. One important task is to predict the future transaction statistics of each merchant. These predictions can thus be used to steer other tasks, ranging from fraud detection to recommendation. This problem is challenging as we need to predict not only multivariate time series but also multi-steps into the future. In this work, we propose a multi-stream RNN model for multi-step merchant transaction predictions tailored to these requirements. The proposed multi-stream RNN summarizes transaction data in different granularity and makes predictions for multiple steps in the future. Our extensive experimental results have demonstrated that the proposed model is capable of outperforming existing state-of-the-art methods.

q-fin.ST↗