arXiv subjects

Xiaohong Guan

Publications and source records attributed to Xiaohong Guan.

At least 55 records · Page 3Linked to original sources

arXiv2021

Infer-AVAE: An Attribute Inference Model Based on Adversarial Variational Autoencoder

User attributes, such as gender and education, face severe incompleteness in social networks. In order to make this kind of valuable data usable for downstream tasks like user profiling and personalized recommendation, attribute inference aims to infer users' missing attribute labels based on observed data. Recently, variational autoencoder (VAE), an end-to-end deep generative model, has shown promising performance by handling the problem in a semi-supervised way. However, VAEs can easily suffer from over-fitting and over-smoothing when applied to attribute inference. To be specific, VAE implemented with multi-layer perceptron (MLP) can only reconstruct input data but fail in inferring missing parts. While using the trending graph neural networks (GNNs) as encoder has the problem that GNNs aggregate redundant information from neighborhood and generate indistinguishable user representations, which is known as over-smoothing. In this paper, we propose an attribute \textbf{Infer}ence model based on \textbf{A}dversarial \textbf{VAE} (Infer-AVAE) to cope with these issues. Specifically, to overcome over-smoothing, Infer-AVAE unifies MLP and GNNs in encoder to learn positive and negative latent representations respectively. Meanwhile, an adversarial network is trained to distinguish the two representations and GNNs are trained to aggregate less noise for more robust representations through adversarial training. Finally, to relieve over-fitting, mutual information constraint is introduced as a regularizer for decoder, so that it can make better use of auxiliary information in representations and generate outputs not limited by observations. We evaluate our model on 4 real-world social network datasets, experimental results demonstrate that our model averagely outperforms baselines by 7.0$\%$ in accuracy.

cs.LG↗

arXiv2021

Wireless Covert Communications Aided by Distributed Cooperative Jamming over Slow Fading Channels

In this paper, we study covert communications between {a pair of} legitimate transmitter-receiver against a watchful warden over slow fading channels. There coexist multiple friendly helper nodes who are willing to protect the covert communication from being detected by the warden. We propose an uncoordinated jammer selection scheme where those helpers whose instantaneous channel gains to the legitimate receiver fall below a pre-established selection threshold will be chosen as jammers radiating jamming signals to defeat the warden. By doing so, the detection accuracy of the warden is expected to be severely degraded while the desired covert communication is rarely affected. We then jointly design the optimal selection threshold and message transmission rate for maximizing covert throughput under the premise that the detection error of the warden exceeds a certain level. Numerical results are presented to validate our theoretical analyses. It is shown that the multi-jammer assisted covert communication outperforms the conventional single-jammer method in terms of covert throughput, and the maximal covert throughput improves significantly as the total number of helpers increases, which demonstrates the validity and superiority of our proposed scheme.

cs.IT↗

arXiv2021

Deferrable Load Scheduling under Demand Charge: A Block Model-Predictive Control Approach

Optimal scheduling of deferrable electrical loads can reshape the aggregated load profile to achieve higher operational efficiency and reliability. This paper studies deferrable load scheduling under demand charge that imposes a penalty on the peak consumption over a billing period. Such a terminal cost poses challenges in real-time dispatch when demand forecasts are inaccurate. A block model-predictive control approach is proposed by breaking demand charge into a sequence of stage costs. The problem of charging electric vehicles is used to illustrate the efficacy of the proposed approach. Numerical examples show that the block model-predictive control outperforms benchmark methods in various settings.

math.OC↗

arXiv2020

Deep Reinforcement Learning for Smart Grid Protection Against Coordinated Multistage Transmission Line Attacks

With the increase of connectivity in power grid, a cascading failure may be triggered by the failure of a transmission line, which can lead to substantial economic losses and serious negative social impacts. Therefore, it is very important to identify the critical lines under various types of attacks that may initiate a cascading failure and deploy defense resources to protect them. Since coordinated multistage line attacks can lead to larger negative impacts compared with a single-stage attack or a multistage attack without coordination, this paper intends to identify the critical lines under coordinated multistage attacks that may initiate a cascading failure and deploy limited defense resources optimally. To this end, we first formulate a total generation loss maximization problem with the consideration of multiple attackers and multiple stages. Due to the large size of solution space, it is very challenging to solve the formulated problem. To overcome the challenge, we reformulate the problem as a Markov game and design its components, e.g., state, action, and reward. Next, we propose a scalable algorithm to solve the Markov game based on multi-agent deep reinforcement learning and prioritized experience replay, which can determine the optimal attacking line sequences. Then, we design a defense strategy to decide the optimal defense line set. Extensive simulation results show the effectiveness of the proposed algorithm and the designed defense strategy.

eess.SY↗

arXiv2020

Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding

We study the problem of node classification on graphs with few-shot novel labels, which has two distinctive properties: (1) There are novel labels to emerge in the graph; (2) The novel labels have only a few representative nodes for training a classifier. The study of this problem is instructive and corresponds to many applications such as recommendations for newly formed groups with only a few users in online social networks. To cope with this problem, we propose a novel Meta Transformed Network Embedding framework (MetaTNE), which consists of three modules: (1) A \emph{structural module} provides each node a latent representation according to the graph structure. (2) A \emph{meta-learning module} captures the relationships between the graph structure and the node labels as prior knowledge in a meta-learning manner. Additionally, we introduce an \emph{embedding transformation function} that remedies the deficiency of the straightforward use of meta-learning. Inherently, the meta-learned prior knowledge can be used to facilitate the learning of few-shot novel labels. (3) An \emph{optimization module} employs a simple yet effective scheduling strategy to train the above two modules with a balance between graph structure learning and meta-learning. Experiments on four real-world datasets show that MetaTNE brings a huge improvement over the state-of-the-art methods.

cs.LG↗

arXiv2020

Learning by Sampling and Compressing: Efficient Graph Representation Learning with Extremely Limited Annotations

Graph convolution network (GCN) attracts intensive research interest with broad applications. While existing work mainly focused on designing novel GCN architectures for better performance, few of them studied a practical yet challenging problem: How to learn GCNs from data with extremely limited annotation? In this paper, we propose a new learning method by sampling strategy and model compression to overcome this challenge. Our approach has multifold advantages: 1) the adaptive sampling strategy largely suppresses the GCN training deviation over uniform sampling; 2) compressed GCN-based methods with a smaller scale of parameters need fewer labeled data to train; 3) the smaller scale of training data is beneficial to reduce the human resource cost to label them. We choose six popular GCN baselines and conduct extensive experiments on three real-world datasets. The results show that by applying our method, all GCN baselines cut down the annotation requirement by as much as 90$\%$ and compress the scale of parameters more than 6$\times$ without sacrificing their strong performance. It verifies that the training method could extend the existing semi-supervised GCN-based methods to the scenarios with the extremely small scale of labeled data.

cs.LG↗

arXiv2020

Can We Trust Your Explanations? Sanity Checks for Interpreters in Android Malware Analysis

With the rapid growth of Android malware, many machine learning-based malware analysis approaches are proposed to mitigate the severe phenomenon. However, such classifiers are opaque, non-intuitive, and difficult for analysts to understand the inner decision reason. For this reason, a variety of explanation approaches are proposed to interpret predictions by providing important features. Unfortunately, the explanation results obtained in the malware analysis domain cannot achieve a consensus in general, which makes the analysts confused about whether they can trust such results. In this work, we propose principled guidelines to assess the quality of five explanation approaches by designing three critical quantitative metrics to measure their stability, robustness, and effectiveness. Furthermore, we collect five widely-used malware datasets and apply the explanation approaches on them in two tasks, including malware detection and familial identification. Based on the generated explanation results, we conduct a sanity check of such explanation approaches in terms of the three metrics. The results demonstrate that our metrics can assess the explanation approaches and help us obtain the knowledge of most typical malicious behaviors for malware analysis.

cs.CR↗

arXiv2020

Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings

In commercial buildings, about 40%-50% of the total electricity consumption is attributed to Heating, Ventilation, and Air Conditioning (HVAC) systems, which places an economic burden on building operators. In this paper, we intend to minimize the energy cost of an HVAC system in a multi-zone commercial building under dynamic pricing with the consideration of random zone occupancy, thermal comfort, and indoor air quality comfort. Due to the existence of unknown thermal dynamics models, parameter uncertainties (e.g., outdoor temperature, electricity price, and number of occupants), spatially and temporally coupled constraints associated with indoor temperature and CO2 concentration, a large discrete solution space, and a non-convex and non-separable objective function, it is very challenging to achieve the above aim. To this end, the above energy cost minimization problem is reformulated as a Markov game. Then, an HVAC control algorithm is proposed to solve the Markov game based on multi-agent deep reinforcement learning with attention mechanism. The proposed algorithm does not require any prior knowledge of uncertain parameters and can operate without knowing building thermal dynamics models. Simulation results based on real-world traces show the effectiveness, robustness and scalability of the proposed algorithm.

eess.SY↗

arXiv2020

Data Based Linearization: Least-Squares Based Approximation

Linearization of power flow is an important topic in power system analysis. The computational burden can be greatly reduced under the linear power flow model while the model error is the main concern. Therefore, various linear power flow models have been proposed in literature and dedicated to seek the optimal approximation. Most linear power flow models are based on some kind of transformation/simplification/Taylor expansion of AC power flow equations and fail to be accurate under cold-start mode. It is surprising that data-based linearization methods have not yet been fully investigated. In this paper, the performance of a data-based least-squares approximation method is investigated. The resulted cold-start sensitive factors are named as least-squares distribution factors (LSDF). Compared with the traditional power transfer distribution factors (PTDF), it is found that the LSDF can work very well for systems with large load variation, and the average error of LSDF is only about 1% of the average error of PTDF. Comprehensive numerical testing is performed and the results show that LSDF has attractive performance in all studied cases and has great application potential in occasions requiring only cold-start linear power flow models.

eess.SY↗

arXiv2020

Harmonics Based Representation in Clarinet Tone Quality Evaluation

Music tone quality evaluation is generally performed by experts. It could be subjective and short of consistency and fairness as well as time-consuming. In this paper we present a new method for identifying the clarinet reed quality by evaluating tone quality based on the harmonic structure and energy distribution. We first decouple the quality of reed and clarinet pipe based on the acoustic harmonics, and discover that the reed quality is strongly relevant to the even parts of the harmonics. Then we construct a features set consisting of the even harmonic envelope and the energy distribution of harmonics in spectrum. The annotated clarinet audio data are recorded from 3 levels of performers and the tone quality is classified by machine learning. The results show that our new method for identifying low and medium high tones significantly outperforms previous methods.

cs.SD↗

arXiv2020

Fast Generating A Large Number of Gumbel-Max Variables

The well-known Gumbel-Max Trick for sampling elements from a categorical distribution (or more generally a nonnegative vector) and its variants have been widely used in areas such as machine learning and information retrieval. To sample a random element $i$ (or a Gumbel-Max variable $i$) in proportion to its positive weight $v_i$, the Gumbel-Max Trick first computes a Gumbel random variable $g_i$ for each positive weight element $i$, and then samples the element $i$ with the largest value of $g_i+\ln v_i$. Recently, applications including similarity estimation and graph embedding require to generate $k$ independent Gumbel-Max variables from high dimensional vectors. However, it is computationally expensive for a large $k$ (e.g., hundreds or even thousands) when using the traditional Gumbel-Max Trick. To solve this problem, we propose a novel algorithm, \emph{FastGM}, that reduces the time complexity from $O(kn^+)$ to $O(k \ln k + n^+)$, where $n^+$ is the number of positive elements in the vector of interest. Instead of computing $k$ independent Gumbel random variables directly, we find that there exists a technique to generate these variables in descending order. Using this technique, our method FastGM computes variables $g_i+\ln v_i$ for all positive elements $i$ in descending order. As a result, FastGM significantly reduces the computation time because we can stop the procedure of Gumbel random variables computing for many elements especially for those with small weights. Experiments on a variety of real-world datasets show that FastGM is orders of magnitude faster than state-of-the-art methods without sacrificing accuracy and incurring additional expenses.

stat.CO↗

arXiv2019

Adversarial Example Detection by Classification for Deep Speech Recognition

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning algorithm. To defend the learning systems from these attacks, existing methods in the speech domain focus on modifying input signals and testing the behaviours of speech recognizers. We, however, formulate the defense as a classification problem and present a strategy for systematically generating adversarial example datasets: one for white-box attacks and one for black-box attacks, containing both adversarial and normal examples. The white-box attack is a gradient-based method on Baidu DeepSpeech with the Mozilla Common Voice database while the black-box attack is a gradient-free method on a deep model-based keyword spotting system with the Google Speech Command dataset. The generated datasets are used to train a proposed Convolutional Neural Network (CNN), together with cepstral features, to detect adversarial examples. Experimental results show that, it is possible to accurately distinct between adversarial and normal examples for known attacks, in both single-condition and multi-condition training settings, while the performance degrades dramatically for unknown attacks. The adversarial datasets and the source code are made publicly available.

cs.LG↗

arXiv2019

Fast Nonconvex SDP Solvers for Large-scale Power System State Estimation

Fast power system state estimation (SE) solution is of paramount importance for achieving real-time decision making in power grid operations. Semidefinite programming (SDP) reformulation has been shown effective to obtain the global optimum for the nonlinear SE problem, while suffering from high computational complexity. Thus, we leverage the recent advances in nonconvex SDP approach that allows for the simple first-order gradient-descent (GD) updates. Using the power system model, we can verify that the SE objective function enjoys nice properties (strongly convex, smoothness) which in turn guarantee a linear convergence rate of the proposed GD-based SE method. To further accelerate the convergence speed, we consider the accelerated gradient descent (AGD) extension, as well as their robust versions under outlier data and a hybrid GD-based SE approach with additional synchrophasor measurements. Numerical tests on the IEEE 118-bus, 300-bus and the synthetic ACTIVSg2000-bus systems have demonstrated that FGD-SE and AGD-SE, can approach the near-optimal performance of the SDP-SE solution at significantly improved computational efficiency, especially so for AGD-SE.

eess.SP↗

arXiv2019

Meta Reinforcement Learning with Task Embedding and Shared Policy

Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL are generally similar at a high level. However, most meta-RL methods do not explicitly and adequately model the specific and shared information among different tasks, which limits their ability to learn training tasks and to generalize to novel tasks. In this paper, we propose to capture the shared information on the one hand and meta-learn how to quickly abstract the specific information about a task on the other hand. Methodologically, we train an SGD meta-learner to quickly optimize a task encoder for each task, which generates a task embedding based on past experience. Meanwhile, we learn a policy which is shared across all tasks and conditioned on task embeddings. Empirical results on four simulated tasks demonstrate that our method has better learning capacity on both training and novel tasks and attains up to 3 to 4 times higher returns compared to baselines.

cs.LG↗

arXiv2019

A Memory-Efficient Sketch Method for Estimating High Similarities in Streaming Sets

Estimating set similarity and detecting highly similar sets are fundamental problems in areas such as databases, machine learning, and information retrieval. MinHash is a well-known technique for approximating Jaccard similarity of sets and has been successfully used for many applications such as similarity search and large scale learning. Its two compressed versions, b-bit MinHash and Odd Sketch, can significantly reduce the memory usage of the original MinHash method, especially for estimating high similarities (i.e., similarities around 1). Although MinHash can be applied to static sets as well as streaming sets, of which elements are given in a streaming fashion and cardinality is unknown or even infinite, unfortunately, b-bit MinHash and Odd Sketch fail to deal with streaming data. To solve this problem, we design a memory efficient sketch method, MaxLogHash, to accurately estimate Jaccard similarities in streaming sets. Compared to MinHash, our method uses smaller sized registers (each register consists of less than 7 bits) to build a compact sketch for each set. We also provide a simple yet accurate estimator for inferring Jaccard similarity from MaxLogHash sketches. In addition, we derive formulas for bounding the estimation error and determine the smallest necessary memory usage (i.e., the number of registers used for a MaxLogHash sketch) for the desired accuracy. We conduct experiments on a variety of datasets, and experimental results show that our method MaxLogHash is about 5 times more memory efficient than MinHash with the same accuracy and computational cost for estimating high similarities.

cs.DS↗

arXiv2019

A Fast Sketch Method for Mining User Similarities over Fully Dynamic Graph Streams

Many real-world networks such as Twitter and YouTube are given as fully dynamic graph streams represented as sequences of edge insertions and deletions. (e.g., users can subscribe and unsubscribe to channels on YouTube). Existing similarity estimation methods such as MinHash and OPH are customized to static graphs. We observe that they are indeed sampling methods and exhibit a sampling bias when applied to fully dynamic graph streams, which results in large estimation errors. To solve this challenge, we develop a fast and accurate sketch method VOS. VOS processes each edge in the graph stream of interest with small time complexity O(1) and uses small memory space to build a compact sketch of the dynamic graph stream over time. Based on the sketch built on-the-fly, we develop a method to estimate user similarities over time. We conduct extensive experiments and the experimental results demonstrate the efficiency and efficacy of our method.

cs.DS↗

arXiv2018

Utilizing Dynamic Properties of Sharing Bits and Registers to Estimate User Cardinalities over Time

Online monitoring user cardinalities (or degrees) in graph streams is fundamental for many applications. For example in a bipartite graph representing user-website visiting activities, user cardinalities (the number of distinct visited websites) are monitored to report network anomalies. These real-world graph streams may contain user-item duplicates and have a huge number of distinct user-item pairs, therefore, it is infeasible to exactly compute user cardinalities when memory and computation resources are limited.Existing methods are designed to approximately estimate user cardinalities, whose accuracy highly depends on parameters that are not easy to set. Moreover, these methods cannot provide anytime-available estimation, as the user cardinalities are computed at the end of the data stream. Real-time applications such as anomaly detection require that user cardinalities are estimated on the fly. To address these problems, we develop novel bit and register sharing algorithms, which use a bit array and a register array to build a compact sketch of all users' connected items respectively. Compared with previous bit and register sharing methods, our algorithms exploit the dynamic properties of the bit and register arrays (e.g., the fraction of zero bits in the bit array at each time) to significantly improve the estimation accuracy, and have low time complexity (O(1)) to update the estimations each time they observe a new user-item pair. In addition, our algorithms are simple and easy to use, without requirements to tune any parameter. We evaluate the performance of our methods on real-world datasets. The experimental results demonstrate that our methods are several times more accurate and faster than state-of-the-art methods using the same amount of memory.

cs.DS↗

arXiv2018

REPT: A Streaming Algorithm of Approximating Global and Local Triangle Counts in Parallel

Recently, considerable efforts have been devoted to approximately computing the global and local (i.e., incident to each node) triangle counts of a large graph stream represented as a sequence of edges. Existing approximate triangle counting algorithms rely on sampling techniques to reduce the computational cost. However, their estimation errors are significantly determined by the covariance between sampled triangles. Moreover, little attention has been paid to developing parallel one-pass streaming algorithms that can be used to fast and approximately count triangles on a multi-core machine or a cluster of machines. To solve these problems, we develop a novel parallel method REPT to significantly reduce the covariance (even completely eliminate the covariance for some cases) between sampled triangles. We theoretically prove that REPT is more accurate than parallelizing existing triangle count estimation algorithms in a direct manner. In addition, we also conduct extensive experiments on a variety of real-world graphs, and the results demonstrate that our method REPT is several times more accurate than state-of-the-art methods.

cs.DS↗