arXiv subjects

Panpan Zhang

Publications and source records attributed to Panpan Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2023

A Strength and Sparsity Preserving Algorithm for Generating Weighted, Directed Networks with Predetermined Assortativity

Degree-preserving rewiring is a widely used technique for generating unweighted networks with given assortativity, but for weighted networks, it is unclear how an analog would preserve the strengths and other critical network features such as sparsity level. This study introduces a novel approach for rewiring weighted networks to achieve desired directed assortativity. The method utilizes a mixed integer programming framework to establish a target network with predetermined assortativity coefficients, followed by an efficient rewiring algorithm termed "strength and sparsity preserving rewiring" (SSPR). SSPR retains the node strength distributions and network sparsity after rewiring. It is also possible to accommodate additional properties like edge weight distribution with extra computational cost. The optimization scheme can be used to determine feasible assortativity ranges for an initial network. The effectiveness of the proposed SSPR algorithm is demonstrated through its application to two classes of popular network models.

stat.CO↗

arXiv2023

Variational Bayesian Inference for Bipartite Mixed-membership Stochastic Block Model with Applications to Collaborative Filtering

Motivated by the connections between collaborative filtering and network clustering, we consider a network-based approach to improving rating prediction in recommender systems. We propose a novel Bipartite Mixed-Membership Stochastic Block Model ($\mathrm{BM}^2$) with a conjugate prior from the exponential family. We derive the analytical expression of the model and introduce a variational Bayesian expectation-maximization algorithm, which is computationally feasible for approximating the untractable posterior distribution. We carry out extensive simulations to show that $\mathrm{BM}^2$ provides more accurate inference than standard SBM with the emergence of outliers. Finally, we apply the proposed model to a MovieLens dataset and find that it outperforms other competing methods for collaborative filtering.

stat.ME↗

arXiv2023

Non-contact PPG Signal and Heart Rate Estimation with Multi-hierarchical Convolutional Network

Heartbeat rhythm and heart rate (HR) are important physiological parameters of the human body. This study presents an efficient multi-hierarchical spatio-temporal convolutional network that can quickly estimate remote physiological (rPPG) signal and HR from face video clips. First, the facial color distribution characteristics are extracted using a low-level face feature generation (LFFG) module. Then, the three-dimensional (3D) spatio-temporal stack convolution module (STSC) and multi-hierarchical feature fusion module (MHFF) are used to strengthen the spatio-temporal correlation of multi-channel features. In the MHFF, sparse optical flow is used to capture the tiny motion information of faces between frames and generate a self-adaptive region of interest (ROI) skin mask. Finally, the signal prediction module (SP) is used to extract the estimated rPPG signal. The heart rate estimation results show that the proposed network overperforms the state-of-the-art methods on three datasets, 1) UBFC-RPPG, 2) COHFACE, 3) our dataset, with the mean absolute error (MAE) of 2.15, 5.57, 1.75 beats per minute (bpm) respectively.

cs.CV↗

arXiv2022

An Efficient Training Approach for Very Large Scale Face Recognition

Face recognition has achieved significant progress in deep learning era due to the ultra-large-scale and welllabeled datasets. However, training on the outsize datasets is time-consuming and takes up a lot of hardware resource. Therefore, designing an efficient training approach is indispensable. The heavy computational and memory costs mainly result from the million-level dimensionality of thefully connected (FC) layer. To this end, we propose a novel training approach, termed Faster Face Classification (F2C), to alleviate time and cost without sacrificing the performance. This method adopts Dynamic Class Pool (DCP) for storing and updating the identities features dynamically, which could be regarded as a substitute for the FC layer. DCP is efficiently time-saving and cost-saving, as its smaller size with the independence from the whole face identities together. We further validate the proposed F2C method across several face benchmarks and private datasets, and display comparable results, meanwhile the speed is faster than state-of-the-art FC-based methods in terms of recognition accuracy and hardware costs. Moreover, our method is further improved by a well-designed dual data loader including indentity-based and instancebased loaders, which makes it more efficient for the updating DCP parameters.

cs.CV↗

arXiv2022

An Efficient Algorithm for Generating Directed Networks with Predetermined Assortativity Measures

Assortativity coefficients are important metrics to analyze both directed and undirected networks. In general, it is not guaranteed that the fitted model will always agree with the assortativity coefficients in the given network, and the structure of directed networks is more complicated than the undirected ones. Therefore, we provide a remedy by proposing a degree-preserving rewiring algorithm, called DiDPR, for generating directed networks with given directed assortativity coefficients. We construct the joint edge distribution of the target network by accounting for the four directed assortativity coefficients simultaneously, provided that they are attainable, and obtain the desired network by solving a convex optimization problem.Our algorithm also helps check the attainability of the given assortativity coefficients. We assess the performance of the proposed algorithm by simulation studies with focus on two different network models, namely Erdös--Rényi and preferential attachment random networks. We then apply the algorithm to a Facebook wall post network as a real data example. The codes for implementing our algorithm are publicly available in R package wdnet.

stat.CO↗

arXiv2021

TEXTOIR: An Integrated and Visualized Platform for Text Open Intent Recognition

TEXTOIR is the first integrated and visualized platform for text open intent recognition. It is composed of two main modules: open intent detection and open intent discovery. Each module integrates most of the state-of-the-art algorithms and benchmark intent datasets. It also contains an overall framework connecting the two modules in a pipeline scheme. In addition, this platform has visualized tools for data and model management, training, evaluation and analysis of the performance from different aspects. TEXTOIR provides useful toolkits and convenient visualized interfaces for each sub-module (Toolkit code: https://github.com/thuiar/TEXTOIR), and designs a framework to implement a complete process to both identify known intents and discover open intents (Demo code: https://github.com/thuiar/TEXTOIR-DEMO).

cs.CL↗

arXiv2021

PageRank centrality and algorithms for weighted, directed networks with applications to World Input-Output Tables

PageRank (PR) is a fundamental tool for assessing the relative importance of the nodes in a network. In this paper, we propose a measure, weighted PageRank (WPR), extended from the classical PR for weighted, directed networks with possible non-uniform node-specific information that is dependent or independent of network structure. A tuning parameter leveraging node degree and strength is introduced. An efficient algorithm based on R program has been developed for computing WPR in large-scale networks. We have tested the proposed WPR on widely used simulated network models, and found it outperformed other competing measures in the literature. By applying the proposed WPR to the real network data generated from World Input-Output Tables, we have seen the results that are consistent with the global economic trends, which renders it a preferred measure in the analysis.

physics.soc-ph↗

arXiv2021

AU-Guided Unsupervised Domain Adaptive Facial Expression Recognition

The domain diversities including inconsistent annotation and varied image collection conditions inevitably exist among different facial expression recognition (FER) datasets, which pose an evident challenge for adapting the FER model trained on one dataset to another one. Recent works mainly focus on domain-invariant deep feature learning with adversarial learning mechanism, ignoring the sibling facial action unit (AU) detection task which has obtained great progress. Considering AUs objectively determine facial expressions, this paper proposes an AU-guided unsupervised Domain Adaptive FER (AdaFER) framework to relieve the annotation bias between different FER datasets. In AdaFER, we first leverage an advanced model for AU detection on both source and target domain. Then, we compare the AU results to perform AU-guided annotating, i.e., target faces that own the same AUs with source faces would inherit the labels from source domain. Meanwhile, to achieve domain-invariant compact features, we utilize an AU-guided triplet training which randomly collects anchor-positive-negative triplets on both domains with AUs. We conduct extensive experiments on several popular benchmarks and show that AdaFER achieves state-of-the-art results on all these benchmarks.

cs.CV↗

arXiv2021

Several topological indices of random caterpillars

In chemical graph theory, caterpillar trees have been an appealing model to represent the molecular structures of benzenoid hydrocarbon. Meanwhile, topological index has been thought of as a powerful tool for modeling quantitative structure-property relationship and quantitative structure-activity between molecules in chemical compounds. In this article, we consider a class of caterpillar trees that are incorporated with randomness, called random caterpillars, and investigate several popular topological indices of this random class, including Zagreb index, Randić index and Wiener index, etc. Especially, a central limit theorem is developed for the asymptotic distribution of the Zagreb index of random caterpillars.

math.PR↗

arXiv2021

Regional and Sectoral Structures and Their Dynamics of Chinese Economy: A Network Perspective from Multi-Regional Input-Output Tables

A multi-regional input-output table (MRIOT) containing the transactions among the region-sectors in an economy defines a weighted and directed network. Using network analysis tools, we analyze the regional and sectoral structure of the Chinese economy and their temporal dynamics from 2007 to 2012 via the MRIOTs of China. Global analyses are done with network topology measures. Growth-driving province-sector clusters are identified with community detection methods. Influential province-sectors are ranked by weighted PageRank scores. The results revealed a few interesting and telling insights. The level of inter-province-sector activities increased with the rapid growth of the national economy, but not as fast as that of intra-province economic activities. Regional community structures were deeply associated with geographical factors. The community heterogeneity across the regions was high and the regional fragmentation increased during the study period. Quantified metrics assessing the relative importance of the province-sectors in the national economy echo the national and regional economic development policies to a certain extent.

physics.soc-ph↗

arXiv2021

Clustering US States by Time Series of COVID-19 New Case Counts with Non-negative Matrix Factorization

The spreading pattern of COVID-19 differ a lot across the US states under different quarantine measures and reopening policies. We proposed to cluster the US states into distinct communities based on the daily new confirmed case counts via a nonnegative matrix factorization (NMF) followed by a k-means clustering procedure on the coefficients of the NMF basis. A cross-validation method was employed to select the rank of the NMF. Applying the method to the entire study period from March 22 to July 25, we clustered the 49 continental states (including District of Columbia) into 7 groups, two of which contained a single state. To investigate the dynamics of the clustering results over time, the same method was successively applied to the time periods with increment of one week, starting from the period of March 22 to March 28. The results suggested a change point in the clustering in the week starting on May 30, which might be explained by a combined impact of both quarantine measures and reopening policies.

stat.AP↗

arXiv2021

Directed Hybrid Random Networks Mixing Preferential Attachment with Uniform Attachment Mechanisms

Motivated by the complexity of network data, we propose a directed hybrid random network that mixes preferential attachment (PA) rules with uniform attachment (UA) rules. When a new edge is created, with probability $p\in [0,1]$, it follows the PA rule. Otherwise, this new edge is added between two uniformly chosen nodes. Such mixture makes the in- and out-degrees of a fixed node grow at a slower rate, compared to the pure PA case, thus leading to lighter distributional tails. Useful inference methods for the proposed hybrid model are then provided and applied to both synthetic and real datasets. We see that with extra flexibility given by the parameter $p$, the hybrid random network provides a better fit to real-world scenarios, where lighter tails from in- and out-degrees are observed.

cs.SI↗

arXiv2021

Assortativity measures for weighted and directed networks

Assortativity measures the tendency of a vertex in a network being connected by other vertexes with respect to some vertex-specific features. Classical assortativity coefficients are defined for unweighted and undirected networks with respect to vertex degree. We propose a class of assortativity coefficients that capture the assortative characteristics and structure of weighted and directed networks more precisely. The vertex-to-vertex strength correlation is used as an example, but the proposed measure can be applied to any pair of vertex-specific features. The effectiveness of the proposed measure is assessed through extensive simulations based on prevalent random network models in comparison with existing assortativity measures. In application World Input-Ouput Networks,the new measures reveal interesting insights that would not be obtained by using existing ones. An implementation is publicly available in a R package "wdnet".

stat.AP↗

arXiv2020

A Unified Model for Recommendation with Selective Neighborhood Modeling

Neighborhood-based recommenders are a major class of Collaborative Filtering (CF) models. The intuition is to exploit neighbors with similar preferences for bridging unseen user-item pairs and alleviating data sparseness. Many existing works propose neural attention networks to aggregate neighbors and place higher weights on specific subsets of users for recommendation. However, the neighborhood information is not necessarily always informative, and the noises in the neighborhood can negatively affect the model performance. To address this issue, we propose a novel neighborhood-based recommender, where a hybrid gated network is designed to automatically separate similar neighbors from dissimilar (noisy) ones, and aggregate those similar neighbors to comprise neighborhood representations. The confidence in the neighborhood is also addressed by putting higher weights on the neighborhood representations if we are confident with the neighborhood information, and vice versa. In addition, a user-neighbor component is proposed to explicitly regularize user-neighbor proximity in the latent space. These two components are combined into a unified model to complement each other for the recommendation task. Extensive experiments on three publicly available datasets show that the proposed model consistently outperforms state-of-the-art neighborhood-based recommenders. We also study different variants of the proposed model to justify the underlying intuition of the proposed hybrid gated network and user-neighbor modeling components.

cs.IR↗

arXiv2020

Characterizing several properties of high-dimensional random Apollonian networks

In this article, we investigate several properties of high-dimensional random Apollonian networks (HDRANs), including two types of degree profiles, the small-world effect (clustering property), sparsity, and three distance-based metrics. The characterizations of degree profiles are based on several rigorous mathematical and probabilistic methods, such as a two-dimensional mathematical induction, analytic combinatorics, and Pólya urns, etc. The small-world property is uncovered by a well-developed measure---local clustering coefficient, and the sparsity is assessed by a proposed Gini index. Finally, we look into three distance-based properties; they are total depth, diameter and Wiener index.

math.PR↗

arXiv2020

Functional data analysis: An application to COVID-19 data in the United States

The COVID-19 pandemic so far has caused huge negative impacts on different areas all over the world, and the United States (US) is one of the most affected countries. In this paper, we use methods from the functional data analysis to look into the COVID-19 data in the US. We explore the modes of variation of the data through a functional principal component analysis (FPCA), and study the canonical correlation between confirmed and death cases. In addition, we run a cluster analysis at the state level so as to investigate the relation between geographical locations and the clustering structure. Lastly, we consider a functional time series model fitted to the cumulative confirmed cases in the US, and make forecasts based on the dynamic FPCA. Both point and interval forecasts are provided, and the methods for assessing the accuracy of the forecasts are also included.

stat.AP↗

arXiv2020

Visual Object Tracking by Segmentation with Graph Convolutional Network

Segmentation-based tracking has been actively studied in computer vision and multimedia. Superpixel based object segmentation and tracking methods are usually developed for this task. However, they independently perform feature representation and learning of superpixels which may lead to sub-optimal results. In this paper, we propose to utilize graph convolutional network (GCN) model for superpixel based object tracking. The proposed model provides a general end-to-end framework which integrates i) label linear prediction, and ii) structure-aware feature information of each superpixel together to obtain object segmentation and further improves the performance of tracking. The main benefits of the proposed GCN method have two main aspects. First, it provides an effective end-to-end way to exploit both spatial and temporal consistency constraint for target object segmentation. Second, it utilizes a mixed graph convolution module to learn a context-aware and discriminative feature for superpixel representation and labeling. An effective algorithm has been developed to optimize the proposed model. Extensive experiments on five datasets demonstrate that our method obtains better performance against existing alternative methods.

cs.CV↗

arXiv2020

DC electricity generation from dynamic polarized water-semiconductor interface

Liquid electricity generator and hydrovoltaic technology have received numerous attentions, which can be divided into horizontal movement generator and vertical movement generator. The horizontal movement generator is limited for powering the integrated and miniaturized energy chip as the current output direction is depending on the moving direction of the water droplet, which means a sustainable and continuous direct-current (DC) electricity output can be hardly achieved because of the film of limited length. On the other hand, the existing vertical movement generators include triboelectricity or humidity gradient-based liquid electricity generator, where the liquid or water resource must be sustainably supplied to ensure continuous current output. Herein, we have designed an integratable vertical generator by sandwiching water droplets with semiconductor and metal, such as graphene or aluminum. This generator, named as polarized liquid molecular generator (PLMG), directly converts the lateral kinetic energy of water droplet into vertical DC electricity with an output voltage of up to ~1.0 V from the dynamic water-semiconductor interface. The fundamental discovery of PLMG is related to the non-symmetric structure of liquid molecules, such as water and alcohols, which can be polarized under the guidance of built-in field caused by the Fermi level difference between metal and semiconductor, while the symmetric liquid molecules cannot produce any electricity on the opposite. Integratable PLMG with a large output power of ~90 nW and voltage of ~2.7 V has been demonstrated, meanwhile its small internal resistance of ~250 kilohm takes a huge advantage in resistance matching with the impedance of electron components. The PLMG shows potential application value in the Internet of Things (IoTs) after proper miniaturization and integration.

physics.app-ph↗