arXiv subjects

Jiang Zhang

Publications and source records attributed to Jiang Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2023

Neural Network Pruning by Gradient Descent

The rapid increase in the parameters of deep learning models has led to significant costs, challenging computational efficiency and model interpretability. In this paper, we introduce a novel and straightforward neural network pruning framework that incorporates the Gumbel-Softmax technique. This framework enables the simultaneous optimization of a network's weights and topology in an end-to-end process using stochastic gradient descent. Empirical results demonstrate its exceptional compression capability, maintaining high accuracy on the MNIST dataset with only 0.15\% of the original network parameters. Moreover, our framework enhances neural network interpretability, not only by allowing easy extraction of feature importance directly from the pruned network but also by enabling visualization of feature symmetry and the pathways of information propagation from features to outcomes. Although the pruning strategy is learned through deep learning, it is surprisingly intuitive and understandable, focusing on selecting key representative features and exploiting data patterns to achieve extreme sparse pruning. We believe our method opens a promising new avenue for deep learning pruning and the creation of interpretable machine learning systems.

cs.LG↗

arXiv2023

A Utility-Preserving Obfuscation Approach for YouTube Recommendations

Online content platforms optimize engagement by providing personalized recommendations to their users. These recommendation systems track and profile users to predict relevant content a user is likely interested in. While the personalized recommendations provide utility to users, the tracking and profiling that enables them poses a privacy issue because the platform might infer potentially sensitive user interests. There is increasing interest in building privacy-enhancing obfuscation approaches that do not rely on cooperation from online content platforms. However, existing obfuscation approaches primarily focus on enhancing privacy but at the same time they degrade the utility because obfuscation introduces unrelated recommendations. We design and implement De-Harpo, an obfuscation approach for YouTube's recommendation system that not only obfuscates a user's video watch history to protect privacy but then also denoises the video recommendations by YouTube to preserve their utility. In contrast to prior obfuscation approaches, De-Harpo adds a denoiser that makes use of a "secret" input (i.e., a user's actual watch history) as well as information that is also available to the adversarial recommendation system (i.e., obfuscated watch history and corresponding "noisy" recommendations). Our large-scale evaluation of De-Harpo shows that it outperforms the state-of-the-art by a factor of 2x in terms of preserving utility for the same level of privacy, while maintaining stealthiness and robustness to de-obfuscation.

cs.CR↗

arXiv2023

Geometric and holonomic quantum computation

Geometric and holonomic quantum computation utilizes intrinsic geometric properties of quantum-mechanical state spaces to realize quantum logic gates. Since both geometric phases and quantum holonomies are global quantities depending only on the evolution paths of quantum systems, quantum gates based on them possess built-in resilience to certain kinds of errors. This review provides an introduction to the topic as well as gives an overview of the theoretical and experimental progress for constructing geometric and holonomic quantum gates and how to combine them with other error-resistant techniques.

quant-ph↗

arXiv2023

Dynamic Graph Neural Network with Adaptive Edge Attributes for Air Quality Predictions

Air quality prediction is a typical spatio-temporal modeling problem, which always uses different components to handle spatial and temporal dependencies in complex systems separately. Previous models based on time series analysis and Recurrent Neural Network (RNN) methods have only modeled time series while ignoring spatial information. Previous GCNs-based methods usually require providing spatial correlation graph structure of observation sites in advance. The correlations among these sites and their strengths are usually calculated using prior information. However, due to the limitations of human cognition, limited prior information cannot reflect the real station-related structure or bring more effective information for accurate prediction. To this end, we propose a novel Dynamic Graph Neural Network with Adaptive Edge Attributes (DGN-AEA) on the message passing network, which generates the adaptive bidirected dynamic graph by learning the edge attributes as model parameters. Unlike prior information to establish edges, our method can obtain adaptive edge information through end-to-end training without any prior information. Thus reduced the complexity of the problem. Besides, the hidden structural information between the stations can be obtained as model by-products, which can help make some subsequent decision-making analyses. Experimental results show that our model received state-of-the-art performance than other baselines.

cs.LG↗

arXiv2023

Tensor networks for unsupervised machine learning

Modeling the joint distribution of high-dimensional data is a central task in unsupervised machine learning. In recent years, many interests have been attracted to developing learning models based on tensor networks, which have the advantages of a principle understanding of the expressive power using entanglement properties, and as a bridge connecting classical computation and quantum computation. Despite the great potential, however, existing tensor network models for unsupervised machine learning only work as a proof of principle, as their performance is much worse than the standard models such as restricted Boltzmann machines and neural networks. In this Letter, we present autoregressive matrix product states (AMPS), a tensor network model combining matrix product states from quantum many-body physics and autoregressive modeling from machine learning. Our model enjoys the exact calculation of normalized probability and unbiased sampling. We demonstrate the performance of our model using two applications, generative modeling on synthetic and real-world data, and reinforcement learning in statistical physics. Using extensive numerical experiments, we show that the proposed model significantly outperforms the existing tensor network models and the restricted Boltzmann machines, and is competitive with state-of-the-art neural network models.

cond-mat.stat-mech↗

arXiv2022

MFV approach to robust estimate of neutron lifetime

Aiming at evaluating the lifetime of the neutron, we introduce a novel statistical method to analyse the updated compilation of precise measurements including the 2022 dataset of Particle Data Group (PDG). Based on the minimization for the information loss principle, unlike the median statistics method, we apply the most frequent value (MFV) procedure to estimate the neutron lifetime, irrespective of the Gaussian or non-Gaussian distributions. Providing a more robust way, the calculated result of the MFV is $τ_n=881.16^{+2.25}_{-2.35}$ s with statistical bootstrap errors, while the result of median statistics is $τ_n=881.5^{+5.5}_{-3}$ s according to the binomial distribution. Using the different central estimates, we also construct the error distributions of neutron lifetime measurements and find the non-Gaussianity, which is still meaningful.

physics.data-an↗

arXiv2022

Extracting lung function-correlated information from CT-encoded static textures

The inherent characteristics of lung tissues, which are independent of breathing manoeuvre, may provide fundamental information on lung function. This paper attempted to study function-correlated lung textures and their spatial distribution from CT. 21 lung cancer patients with thoracic 4DCT scans, DTPA-SPECT ventilation images (V), and available pulmonary function test (PFT) measurements were collected. 79 radiomic features were included for analysis, and a sparse-to-fine strategy including subregional feature discovery and voxel-wise feature distribution study was carried out to identify the function-correlated radiomic features. At the subregion level, lung CT images were partitioned and labeled as defected/non-defected patches according to reference V. At the voxel-wise level, feature maps (FMs) of selected feature candidates were generated for each 4DCT phase. Quantitative metrics, including Spearman coefficient of correlation (SCC) and Dice similarity coefficient (DSC) for FM-V spatial agreement assessments, intra-class coefficient of correlation (ICC) for FM robustness evaluations, and FM-PFT comparisons, were applied to validate the results. At the subregion level, eight function-correlated features were filtered out with medium-to-large statistical strength (effect size>0.330) to differentiate defected/non-defected lung regions. At the voxel-wise level, FMs of candidates yielded moderate-to-strong voxel-wise correlations with reference V. Among them, FMs of GLDM Dependence Non-uniformity showed the highest robust (ICC=0.96) spatial correlation, with median SCCs ranging from 0.54 to 0.59 throughout ten phases. Its phase-averaged FM achieved a median SCC of 0.60, the median DSC of 0.60/0.65 for high/low functional lung volumes, respectively, and the correlation of 0.646 between the spatially averaged feature values and PFT measurements.

physics.med-ph↗

arXiv2022

Multi-view Contrastive Learning with Additive Margin for Adaptive Nasopharyngeal Carcinoma Radiotherapy Prediction

The prediction of adaptive radiation therapy (ART) prior to radiation therapy (RT) for nasopharyngeal carcinoma (NPC) patients is important to reduce toxicity and prolong the survival of patients. Currently, due to the complex tumor micro-environment, a single type of high-resolution image can provide only limited information. Meanwhile, the traditional softmax-based loss is insufficient for quantifying the discriminative power of a model. To overcome these challenges, we propose a supervised multi-view contrastive learning method with an additive margin (MMCon). For each patient, four medical images are considered to form multi-view positive pairs, which can provide additional information and enhance the representation of medical images. In addition, the embedding space is learned by means of contrastive learning. NPC samples from the same patient or with similar labels will remain close in the embedding space, while NPC samples with different labels will be far apart. To improve the discriminative ability of the loss function, we incorporate a margin into the contrastive learning. Experimental result show this new learning objective can be used to find an embedding space that exhibits superior discrimination ability for NPC images.

cs.CV↗

arXiv2022

Neural Information Squeezer for Causal Emergence

The classic studies of causal emergence have revealed that in some Markovian dynamical systems, far stronger causal connections can be found on the higher-level descriptions than the lower-level of the same systems if we coarse-grain the system states in an appropriate way. However, identifying this emergent causality from the data is still a hard problem that has not been solved because the correct coarse-graining strategy can not be found easily. This paper proposes a general machine learning framework called Neural Information Squeezer to automatically extract the effective coarse-graining strategy and the macro-state dynamics, as well as identify causal emergence directly from the time series data. By decomposing a coarse-graining operation into two processes: information conversion and information dropping out, we can not only exactly control the width of the information channel, but also can derive some important properties analytically including the exact expression of the effective information of a macro-dynamics. We also show how our framework can extract the dynamics on different levels and identify causal emergence from the data on several exampled systems.

cs.LG↗

arXiv2022

Expectation-Maximizing Network Reconstruction and MostApplicable Network Types Based on Binary Time Series Data

Based on the binary time series data of social infection dynamics, we propose a general framework to reconstruct 2-simplex complexes with two-body and three-body interactions by combining the maximum likelihood estimation in statistical inference and introducing the expectation maximization. In order to improve the code running efficiency, the whole algorithm adopts vectorization expression. Through the inference of maximum likelihood estimation, the vectorization expression of the edge existence probability can be obtained, and through the probability matrix, the adjacency matrix of the network can be estimated. We apply a two-step scheme to improve the effectiveness of network reconstruction while reducing the amount of computation significantly. The framework has been tested on different types of complex networks. Among them, four kinds of networks can obtain high reconstruction effectiveness. Besides, we study the influence of noise data or random interference and prove the robustness of the framework, then the effects of two kinds of hyper-parameters on the experimental results are tested. Finally, we analyze which type of network is more suitable for this framework, and propose methods to improve the effectiveness of the experimental results.

physics.soc-ph↗

arXiv2022

Completing Networks by Learning Local Connection Patterns

Network completion is a harder problem than link prediction because it does not only try to infer missing links but also nodes. Different methods have been proposed to solve this problem, but few of them employed structural information - the similarity of local connection patterns. In this paper, we propose a model named C-GIN to capture the local structural patterns from the observed part of a network based on the Graph Auto-Encoder framework equipped with Graph Isomorphism Network model and generalize these patterns to complete the whole graph. Experiments and analysis on synthetic and real-world networks from different domains show that competitive performance can be achieved by C-GIN with less information being needed, and higher accuracy compared with baseline prediction models in most cases can be obtained. We further proposed a metric "Reachable Clustering Coefficient(CC)" based on network structure. And experiments show that our model perform better on a network with higher Reachable CC.

cs.LG↗

arXiv2022

How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?

Federated learning (FL) has attracted growing interest for enabling privacy-preserving machine learning on data stored at multiple users while avoiding moving the data off-device. However, while data never leaves users' devices, privacy still cannot be guaranteed since significant computations on users' training data are shared in the form of trained local models. These local models have recently been shown to pose a substantial privacy threat through different privacy attacks such as model inversion attacks. As a remedy, Secure Aggregation (SA) has been developed as a framework to preserve privacy in FL, by guaranteeing the server can only learn the global aggregated model update but not the individual model updates. While SA ensures no additional information is leaked about the individual model update beyond the aggregated model update, there are no formal guarantees on how much privacy FL with SA can actually offer; as information about the individual dataset can still potentially leak through the aggregated model computed at the server. In this work, we perform a first analysis of the formal privacy guarantees for FL with SA. Specifically, we use Mutual Information (MI) as a quantification metric and derive upper bounds on how much information about each user's dataset can leak through the aggregated model update. When using the FedSGD aggregation algorithm, our theoretical bounds show that the amount of privacy leakage reduces linearly with the number of users participating in FL with SA. To validate our theoretical bounds, we use an MI Neural Estimator to empirically evaluate the privacy leakage under different FL setups on both the MNIST and CIFAR10 datasets. Our experiments verify our theoretical bounds for FedSGD, which show a reduction in privacy leakage as the number of users and local batch size grow, and an increase in privacy leakage with the number of training rounds.

cs.LG↗

arXiv2022

Scaling laws and a general theory for the growth of public companies

Publicly traded companies are fundamental units of contemporary economies and markets and are important mechanisms through which humans interact with their environments. Understanding the general properties that underlie the processes of their growth has long been of interest, yet fundamental debates about the effects of firm size on growth have persisted. Here we develop a scaling framework that focuses on company size as the critical feature determining a variety of tradeoffs, and use this to reveal novel systematic behavior across the diversity of publicly-traded companies. Using a large database of 31,553 US companies over nearly 70 years, and 3,160 Chinese companies over 24 year, we show how the dynamics of companies expressed as scaling relationships leads to a quantitative, analytic theory for their growth. This theory produces several predictions that are in good agreement with data for both the US and China, whose markets have strikingly different histories and underlying structures. In both cases sales scale sublinearly with assets and exhibit nearly identical exponents leading, surprisingly and nontrivially, to assets that grow as a power law in time rather than exponentially, as often assumed. On the other hand, liabilities scale linearly in the US (exponent of $1.0$) but superlinearly in China (exponent of $1.09$). We show that such small differences in scaling exponents can have a significant impact on the character and long-term evolution of growth trajectories. These results illustrate that while companies are part of a larger class of growth phenomena driven by incomes and costs that scale with size, they are unique in that they grow following a temporal power-function which sets them apart from organisms, cities, nations, and markets, whose growth over time is often exponential.

physics.soc-ph↗

arXiv2022

A Universal Framework for Reconstructing Complex Networks and Node Dynamics from Discrete or Continuous Dynamics Data

Many dynamical processes of complex systems can be understood as the dynamics of a group of nodes interacting on a given network structure. However, finding such interaction structure and node dynamics from time series of node behaviours is tough. Conventional methods focus on either network structure inference task or dynamics reconstruction problem, very few of them can work well on both. This paper proposes a universal framework for reconstructing network structure and node dynamics at the same time from observed time-series data of nodes. We use a differentiable Bernoulli sampling process to generate a candidate network structure, and use neural networks to simulate the node dynamics based on the candidate network. We then adjust all the parameters with a stochastic gradient descent algorithm to maximize the likelihood function defined on the data. The experiments show that our model can recover various network structures and node dynamics at the same time with high accuracy. It can also work well on binary, discrete and continuous time-series data, and the reconstruction results are robust against noise and missing information.

physics.soc-ph↗

arXiv2022

Inferring Network Structure with Unobservable Nodes from Time Series Data

Network structures play important roles in social, technological and biological systems. However, the observable nodes and connections in real cases are often incomplete or unavailable due to measurement errors, private protection issues, or other problems. Therefore, inferring the complete network structure is useful for understanding human interactions and complex dynamics. The existing studies have not fully solved the problem of inferring network structure with partial information about connections or nodes. In this paper, we tackle the problem by utilizing time-series data generated by network dynamics. We regard the network inference problem based on dynamical time series data as a problem of minimizing errors for predicting states of observable nodes and proposed a novel data-driven deep learning model called Gumbel-softmax Inference for Network (GIN) to solve the problem under incomplete information. The GIN framework includes three modules: a dynamics learner, a network generator, and an initial state generator to infer the unobservable parts of the network. We implement experiments on artificial and empirical social networks with discrete and continuous dynamics. The experiments show that our method can infer the unknown parts of the structure and the initial states of the observable nodes with up to 90\% accuracy. The accuracy declines linearly with the increase of the fractions of unobservable nodes. Our framework may have wide applications where the network structure is hard to obtain and the time series data is rich.

cs.SI↗

arXiv2022

NEDMP: Neural Enhanced Dynamic Message Passing

Predicting stochastic spreading processes on complex networks is critical in epidemic control, opinion propagation, and viral marketing. We focus on the problem of inferring the time-dependent marginal probabilities of states for each node which collectively quantifies the spreading results. Dynamic Message Passing (DMP) has been developed as an efficient inference algorithm for several spreading models, and it is asymptotically exact on locally tree-like networks. However, DMP can struggle in diffusion networks with lots of local loops. We address this limitation by using Graph Neural Networks (GNN) to learn the dependency amongst messages implicitly. Specifically, we propose a hybrid model in which the GNN module runs jointly with DMP equations. The GNN module refines the aggregated messages in DMP iterations by learning from simulation data. We demonstrate numerically that after training, our model's inference accuracy substantially outperforms DMP in conditions of various network structure and dynamics parameters. Moreover, compared to pure data-driven models, the proposed hybrid model has a better generalization ability for out-of-training cases, profiting from the explicitly utilized dynamics priors in the hybrid model. A PyTorch implementation of our model is at https://github.com/FeiGSSS/NEDMP.

cs.SI↗

arXiv2022

Privacy-Utility Trades in Crowdsourced Signal Map Obfuscation

Cellular providers and data aggregating companies crowdsource celluar signal strength measurements from user devices to generate signal maps, which can be used to improve network performance. Recognizing that this data collection may be at odds with growing awareness of privacy concerns, we consider obfuscating such data before the data leaves the mobile device. The goal is to increase privacy such that it is difficult to recover sensitive features from the obfuscated data (e.g. user ids and user whereabouts), while still allowing network providers to use the data for improving network services (i.e. create accurate signal maps). To examine this privacy-utility tradeoff, we identify privacy and utility metrics and threat models suited to signal strength measurements. We then obfuscate the measurements using several preeminent techniques, spanning differential privacy, generative adversarial privacy, and information-theoretic privacy techniques, in order to benchmark a variety of promising obfuscation approaches and provide guidance to real-world engineers who are tasked to build signal maps that protect privacy without hurting utility. Our evaluation results, based on multiple, diverse, real-world signal map datasets, demonstrate the feasibility of concurrently achieving adequate privacy and utility, with obfuscation strategies which use the structure and intended use of datasets in their design, and target average-case, rather than worst-case, guarantees.

cs.CR↗

arXiv2022

Role of surface functional groups to superconductivity in Nb$_2$C-MXene: Experiments and density functional theory calculations

The recently discovered surface-group-dependent superconductivity in Nb$_2$C-MXene fabricated by the molten salts method is attracting wide attention. However, regarding the superconductivity of Nb$_2$C-MXene with functional F groups (Nb$_2$CF$_x$), there were some conflicting results in experimental and theoretical studies. Herein, we systematically carried out experimental and theoretical investigations on the superconductivity in Nb$_2$C-MXene with the Cl functional group (Nb$_2$CCl$_x$) and Nb$_2$CF$_x$. The experimental results of the Meissner effect and zero resistivity have proved that Nb$_2$CClx is superconducting with the transition temperature (Tc) ~ 5.2 K. We extract its superconducting parameters from the temperature dependence of resistivity and the field dependence of the magnetization. The Ginzburg-Landau parameter K$_G$$_L$ is estimated to be 2.41, indicating that Nb$_2$CClx is a typical type-II superconductor. Conversely, both magnetic and electrical transport measurements demonstrate that Nb$_2$CF$_x$ is not superconducting. The first-principles density functional theory (DFT) calculations show that the Tc of Nb$_2$Cl$_x$ is ~ 5.2 K, while Nb$_2$CF$_x$ is dynamically unstable with imaginary frequency in phonon spectrum, which is in good agreement with the experimental results. Our studies not only are useful for clarifying the present inconsistency but also offer referential significance for future investigations on the superconductivity of MXenes.

cond-mat.supr-con↗