
Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
Many realworld IoT systems comprising various internetconnected sensor...
read it

Improved Estimation of Concentration Under ℓ_pNorm Distance Metrics Using Half Spaces
Concentration of measure has been argued to be the fundamental cause of ...
read it

Interpretable Deep Learning: Interpretations, Interpretability, Trustworthiness, and Beyond
Deep neural networks have been wellknown for their superb performance i...
read it

MultiTask Time Series Forecasting With Shared Attention
Time series forecasting is a key component in many industrial and busine...
read it

Modeling Heterogeneous Relations across Multiple Modes for Potential Crowd Flow Prediction
Potential crowd flow prediction for new planned transportation sites is ...
read it

Guidance Module Network for Video Captioning
Video captioning has been a challenging and significant task that descri...
read it

SelfSupervised Visual Representation Learning from Hierarchical Grouping
We create a framework for bootstrapping visual representation learning f...
read it

Semisupervised Autoencoding Projective Dependency Parsing
We describe two endtoend autoencoding models for semisupervised graph...
read it

CrossLingual Document Retrieval with Smooth Learning
Crosslingual document search is an information retrieval task in which ...
read it

Measuring Information Transfer in Neural Networks
Estimation of the information content in a neural network model can be p...
read it

Variance Reduction for Deep QLearning using Stochastic Recursive Gradient
Deep Qlearning algorithms often suffer from poor gradient estimations w...
read it

Solving the BetheSalpeter equation on massively parallel architectures
The last ten years have witnessed fast spreading of massively parallel c...
read it

Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
Overparameterized deep neural networks (DNNs) with sufficient capacity ...
read it

Weighted directed networks with a differentially private bidegree sequence
The p_0 model is an exponential random graph model for directed networks...
read it

CoinMagic: A Differential Privacy Framework for Ring Signature Schemes
By allowing users to obscure their transactions via including "mixins" (...
read it

Nearly Optimal Risk Bounds for Kernel KMeans
In this paper, we study the statistical properties of the kernel kmeans...
read it

Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
Starting with Gilmer et al. (2018), several works have demonstrated the ...
read it

Learning Adversarially Robust Representations via WorstCase Mutual Information Maximization
Training machine learning models to be robust against adversarial inputs...
read it

Labelguided Learning for Text Classification
Text classification is one of the most important and fundamental tasks i...
read it

Tiny Noise Can Make an EEGBased BrainComputer Interface Speller Output Anything
An electroencephalogram (EEG) based braincomputer interface (BCI) spell...
read it

Tensor Graph Convolutional Networks for Text Classification
Compared to sequential learning models, graphbased neural networks exhi...
read it

Empirical Studies on the Properties of Linear Regions in Deep Neural Networks
A deep neural network (DNN) with piecewise linear activations can partit...
read it

Learn to Segment Retinal Lesions and Beyond
Towards automated retinal screening, this paper makes an endeavor to sim...
read it

Universal Adversarial Perturbations for CNN Classifiers in EEGBased BCIs
Multiple convolutional neural network (CNN) classifiers have been propos...
read it

An Anomaly Contribution Explainer for CyberSecurity Applications
In this paper, we introduce Anomaly Contribution Explainer or ACE, a too...
read it

Active Learning for BlackBox Adversarial Attacks in EEGBased BrainComputer Interfaces
Deep learning has made significant breakthroughs in many fields, includi...
read it

An Adaptive Empirical Bayesian Method for Sparse Deep Learning
We propose a novel adaptive empirical Bayesian (AEB) method for sparse d...
read it

SegSort: Segmentation by Discriminative Sorting of Segments
Almost all existing deep learning approaches for semantic segmentation t...
read it

Lowcost LIDAR based Vehicle Pose Estimation and Tracking
Detecting surrounding vehicles by lowcost LIDAR has been drawing enormo...
read it

Learning ConceptualContexual Embeddings for Medical Text
External knowledge is often useful for natural language understanding ta...
read it

The iMaterialist Fashion Attribute Dataset
Largescale image databases such as ImageNet have significantly advanced...
read it

Sentiment Tagging with Partial Labels using Modular Architectures
Many NLP learning tasks can be decomposed into several distinct subtask...
read it

Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
Many recent works have shown that adversarial examples that fool classif...
read it

Joint Learning of Neural Networks via Iterative Reweighted Least Squares
In this paper, we introduce the problem of jointly learning feedforward...
read it

P2SGrad: Refined Gradients for Optimizing Deep Face Models
Cosinebased softmax losses significantly improve the performance of dee...
read it

AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
The cosinebased softmax losses and their variants achieve great success...
read it

Normalized Diversification
Generating diverse yet specific data is the goal of the generative adver...
read it

On the Vulnerability of CNN Classifiers in EEGBased BCIs
Deep learning has been successfully used in numerous applications becaus...
read it

Optimal deployment of sustainable UAV networks for providing wireless coverage
Each UAV is constrained in its energy storage and wireless coverage, and...
read it

DeeperLab: SingleShot Image Parser
We present a singleshot, bottomup approach for whole image parsing. Wh...
read it

Delta Embedding Learning
Learning from corpus and learning from supervised NLP tasks both give us...
read it

CostSensitive Robustness against Adversarial Examples
Several recent works have developed methods for training classifiers tha...
read it

Learning Onehiddenlayer ReLU Networks via Gradient Descent
We study the problem of learning onehiddenlayer neural networks with R...
read it

Economics of UAVaided Mobile Services Deployment
An Unmanned Aerial Vehicle (UAV) network has emerged as a promising tech...
read it

OMG  Emotion Challenge Solution
This short paper describes our solution to the 2018 IEEE World Congress ...
read it

NetAdapt: PlatformAware Neural Network Adaptation for Mobile Applications
This work proposes an automated algorithm, called NetAdapt, that adapts ...
read it

Learning architectures based on quantum entanglement: a simple matrix product state algorithm for image recognition
It is a fundamental, but still elusive question whether methods based on...
read it

Fast and Sample Efficient Inductive Matrix Completion via MultiPhase Procrustes Flow
We revisit the inductive matrix completion problem that aims to recover ...
read it

Medical Exam Question Answering with Largescale Reading Comprehension
Reading and understanding text is one important component in computer ai...
read it

Optimal Deployment of UAV Networks for Delivering Emergency Wireless Coverage
Unmanned Aerial Vehicle (UAV) networks have emerged as a promising techn...
read it
Xiao Zhang
verfied profile