arXiv subjects

Jun Wu

Publications and source records attributed to Jun Wu.

At least 145 records · Page 8Linked to original sources

arXiv2023

Partial Homoscedasticity in Causal Discovery with Linear Models

Recursive linear structural equation models and the associated directed acyclic graphs (DAGs) play an important role in causal discovery. The classic identifiability result for this class of models states that when only observational data is available, each DAG can be identified only up to a Markov equivalence class. In contrast, recent work has shown that the DAG can be uniquely identified if the errors in the model are homoscedastic, i.e., all have the same variance. This equal variance assumption yields methods that, if appropriate, are highly scalable and also sheds light on fundamental information-theoretic limits and optimality in causal discovery. In this paper, we fill the gap that exists between the two previously considered cases, which assume the error variances to be either arbitrary or all equal. Specifically, we formulate a framework of partial homoscedasticity, in which the variables are partitioned into blocks and each block shares the same error variance. For any such groupwise equal variances assumption, we characterize when two DAGs give rise to identical Gaussian linear structural equation models. Furthermore, we show how the resulting distributional equivalence classes may be represented using a completed partially directed acyclic graph (CPDAG), and we give an algorithm to efficiently construct this CPDAG. In a simulation study, we demonstrate that greedy search provides an effective way to learn the CPDAG and exploit partial knowledge about homoscedasticity of errors in structural equation models.

math.ST↗

arXiv2023

MedLens: Improve Mortality Prediction Via Medical Signs Selecting and Regression

Monitoring the health status of patients and predicting mortality in advance is vital for providing patients with timely care and treatment. Massive medical signs in electronic health records (EHR) are fitted into advanced machine learning models to make predictions. However, the data-quality problem of original clinical signs is less discussed in the literature. Based on an in-depth measurement of the missing rate and correlation score across various medical signs and a large amount of patient hospital admission records, we discovered the comprehensive missing rate is extremely high, and a large number of useless signs could hurt the performance of prediction models. Then we concluded that only improving data-quality could improve the baseline accuracy of different prediction algorithms. We designed MEDLENS, with an automatic vital medical signs selection approach via statistics and a flexible interpolation approach for high missing rate time series. After augmenting the data-quality of original medical signs, MEDLENS applies ensemble classifiers to boost the accuracy and reduce the computation overhead at the same time. It achieves a very high accuracy performance of 0.96 AUC-ROC and 0.81 AUC-PR, which exceeds the previous benchmark.

cs.LG↗

arXiv2023

Physics-Informed Deep Learning to Reduce the Bias in Joint Prediction of Nitrogen Oxides

Atmospheric nitrogen oxides (NOx) primarily from fuel combustion have recognized acute and chronic health and environmental effects. Machine learning (ML) methods have significantly enhanced our capacity to predict NOx concentrations at ground-level with high spatiotemporal resolution but may suffer from high estimation bias since they lack physical and chemical knowledge about air pollution dynamics. Chemical transport models (CTMs) leverage this knowledge; however, accurate predictions of ground-level concentrations typically necessitate extensive post-calibration. Here, we present a physics-informed deep learning framework that encodes advection-diffusion mechanisms and fluid dynamics constraints to jointly predict NO2 and NOx and reduce ML model bias by 21-42%. Our approach captures fine-scale transport of NO2 and NOx, generates robust spatial extrapolation, and provides explicit uncertainty estimation. The framework fuses knowledge-driven physicochemical principles of CTMs with the predictive power of ML for air quality exposure, health, and policy applications. Our approach offers significant improvements over purely data-driven ML methods and has unprecedented bias reduction in joint NO2 and NOx prediction.

cs.LG↗

arXiv2023

Differentially Private Graph Neural Network with Importance-Grained Noise Adaption

Graph Neural Networks (GNNs) with differential privacy have been proposed to preserve graph privacy when nodes represent personal and sensitive information. However, the existing methods ignore that nodes with different importance may yield diverse privacy demands, which may lead to over-protect some nodes and decrease model utility. In this paper, we study the problem of importance-grained privacy, where nodes contain personal data that need to be kept private but are critical for training a GNN. We propose NAP-GNN, a node-importance-grained privacy-preserving GNN algorithm with privacy guarantees based on adaptive differential privacy to safeguard node information. First, we propose a Topology-based Node Importance Estimation (TNIE) method to infer unknown node importance with neighborhood and centrality awareness. Second, an adaptive private aggregation method is proposed to perturb neighborhood aggregation from node-importance-grain. Third, we propose to privately train a graph learning algorithm on perturbed aggregations in adaptive residual connection mode over multi-layers convolution for node-wise tasks. Theoretically analysis shows that NAP-GNN satisfies privacy guarantees. Empirical experiments over real-world graph datasets show that NAP-GNN achieves a better trade-off between privacy and accuracy.

cs.LG↗

arXiv2023

Hierarchical Codebook Design and Analytical Beamforming Solution for IRS Assisted Communication

In intelligent reflecting surface (IRS) assisted communication, beam search is usually time-consuming as the multiple-input multiple-output (MIMO) of IRS is usually very large. Hierarchical codebooks is a widely accepted method for reducing the complexity of searching time. The performance of this method strongly depends on the design scheme of beamforming of different beamwidths. In this paper, a non-constant phase difference (NCPD) beamforming algorithm is proposed. To implement the NCPD algorithm, we first model the phase shift of IRS as a continuous function, and then determine the parameters of the continuous function through the analysis of its array factor. Then, we propose a hierarchical codebook and two beam training schemes, namely the joint searching (JS) scheme and direction-wise searching (DWS) scheme by using the NCPD algorithm which can flexibly change the width, direction and shape of the beam formed by the IRS array. Simulation results show that the NCPD algorithm is more accurate with smaller side lobes, and also more stable on IRS of different sizes compared to other wide beam algorithms. The misalignment rate of the beam formed by the NCPD method is significantly reduced. The time complexity of the NCPD algorithm is constant, thus making it more suitable for solving the beamforming design problem with practically large IRS.

cs.IT↗

arXiv2023

Identifiability of Homoscedastic Linear Structural Equation Models using Algebraic Matroids

We consider structural equation models (SEMs), in which every variable is a function of a subset of the other variables and a stochastic error. Each such SEM is naturally associated with a directed graph describing the relationships between variables. When the errors are homoscedastic, recent work has proposed methods for inferring the graph from observational data under the assumption that the graph is acyclic (i.e., the SEM is recursive). In this work, we study the setting of homoscedastic errors but allow the graph to be cyclic (i.e., the SEM to be non-recursive). Using an algebraic approach that compares matroids derived from the parameterizations of the models, we derive sufficient conditions for when two simple directed graphs generate different distributions generically. Based on these conditions, we exhibit subclasses of graphs that allow for directed cycles, yet are generically identifiable. We also conjecture a strengthening of our graphical criterion which can be used to distinguish many more non-complete graphs.

math.CO↗

arXiv2023

From Bi-Level to One-Level: A Framework for Structural Attacks to Graph Anomaly Detection

The success of graph neural networks stimulates the prosperity of graph mining and the corresponding downstream tasks including graph anomaly detection (GAD). However, it has been explored that those graph mining methods are vulnerable to structural manipulations on relational data. That is, the attacker can maliciously perturb the graph structures to assist the target nodes to evade anomaly detection. In this paper, we explore the structural vulnerability of two typical GAD systems: unsupervised FeXtra-based GAD and supervised GCN-based GAD. Specifically, structural poisoning attacks against GAD are formulated as complex bi-level optimization problems. Our first major contribution is then to transform the bi-level problem into one-level leveraging different regression methods. Furthermore, we propose a new way of utilizing gradient information to optimize the one-level optimization problem in the discrete domain. Comprehensive experiments demonstrate the effectiveness of our proposed attack algorithm BinarizedAttack.

cs.CR↗

arXiv2023

When UAVs Meet ISAC: Real-Time Trajectory Design for Secure Communications

The real-time unmanned aerial vehicle (UAV) trajectory design of secure integrated sensing and communication (ISAC) is optimized. In particular, the UAV serves both as a downlink transmitter and a radar receiver. The legitimate user (Bob) roams on ground through a series of unknown locations, while the eavesdropper moves following a fixed known trajectory. To maximize the real-time secrecy rate, we propose an extended Kalman filtering (EKF)-based method for tracking and predicting Bob's location at the UAV based on the delay measurements extracted from the sensing echoes. We then formulate a non-convex real-time trajectory design problem and develop an efficient iterative algorithm for finding a near optimal solution. Our numerical results demonstrate that the proposed algorithm is capable of accurately tracking Bob and strikes a compelling legitimate vs. leakage rate trade-off.

eess.SP↗

arXiv2023

Privacy Inference-Empowered Stealthy Backdoor Attack on Federated Learning under Non-IID Scenarios

Federated learning (FL) naturally faces the problem of data heterogeneity in real-world scenarios, but this is often overlooked by studies on FL security and privacy. On the one hand, the effectiveness of backdoor attacks on FL may drop significantly under non-IID scenarios. On the other hand, malicious clients may steal private data through privacy inference attacks. Therefore, it is necessary to have a comprehensive perspective of data heterogeneity, backdoor, and privacy inference. In this paper, we propose a novel privacy inference-empowered stealthy backdoor attack (PI-SBA) scheme for FL under non-IID scenarios. Firstly, a diverse data reconstruction mechanism based on generative adversarial networks (GANs) is proposed to produce a supplementary dataset, which can improve the attacker's local data distribution and support more sophisticated strategies for backdoor attacks. Based on this, we design a source-specified backdoor learning (SSBL) strategy as a demonstration, allowing the adversary to arbitrarily specify which classes are susceptible to the backdoor trigger. Since the PI-SBA has an independent poisoned data synthesis process, it can be integrated into existing backdoor attacks to improve their effectiveness and stealthiness in non-IID scenarios. Extensive experiments based on MNIST, CIFAR10 and Youtube Aligned Face datasets demonstrate that the proposed PI-SBA scheme is effective in non-IID FL and stealthy against state-of-the-art defense methods.

cs.LG↗

arXiv2023

Optimizing the Collaboration Structure in Cross-Silo Federated Learning

In federated learning (FL), multiple clients collaborate to train machine learning models together while keeping their data decentralized. Through utilizing more training data, FL suffers from the potential negative transfer problem: the global FL model may even perform worse than the models trained with local data only. In this paper, we propose FedCollab, a novel FL framework that alleviates negative transfer by clustering clients into non-overlapping coalitions based on their distribution distances and data quantities. As a result, each client only collaborates with the clients having similar data distributions, and tends to collaborate with more clients when it has less data. We evaluate our framework with a variety of datasets, models, and types of non-IIDness. Our results demonstrate that FedCollab effectively mitigates negative transfer across a wide range of FL algorithms and consistently outperforms other clustered FL algorithms.

cs.LG↗

arXiv2023

FakeSwarm: Improving Fake News Detection with Swarming Characteristics

The proliferation of fake news poses a serious threat to society, as it can misinform and manipulate the public, erode trust in institutions, and undermine democratic processes. To address this issue, we present FakeSwarm, a fake news identification system that leverages the swarming characteristics of fake news. To extract the swarm behavior, we propose a novel concept of fake news swarming characteristics and design three types of swarm features, including principal component analysis, metric representation, and position encoding. We evaluate our system on a public dataset and demonstrate the effectiveness of incorporating swarm features in fake news identification, achieving an f1-score and accuracy of over 97% by combining all three types of swarm features. Furthermore, we design an online learning pipeline based on the hypothesis of the temporal distribution pattern of fake news emergence, validated on a topic with early emerging fake news and a shortage of text samples, showing that swarm features can significantly improve recall rates in such cases. Our work provides a new perspective and approach to fake news detection and highlights the importance of considering swarming characteristics in detecting fake news.

cs.SI↗

arXiv2023

BotTriNet: A Unified and Efficient Embedding for Social Bots Detection via Metric Learning

The rapid and accurate identification of bot accounts in online social networks is an ongoing challenge. In this paper, we propose BOTTRINET, a unified embedding framework that leverages the textual content posted by accounts to detect bots. Our approach is based on the premise that account personalities and habits can be revealed through their contextual content. To achieve this, we designed a triplet network that refines raw embeddings using metric learning techniques. The BOTTRINET framework produces word, sentence, and account embeddings, which we evaluate on a real-world dataset, CRESCI2017, consisting of three bot account categories and five bot sample sets. Our approach achieves state-of-the-art performance on two content-intensive bot sets, with an average accuracy of 98.34% and f1score of 97.99%. Moreover, our method makes a significant breakthrough on four content-less bot sets, with an average accuracy improvement of 11.52% and an average f1score increase of 16.70%. Our contribution is twofold: First, we propose a unified and effective framework that combines various embeddings for bot detection. Second, we demonstrate that metric learning techniques can be applied in this context to refine raw embeddings and improve classification performance. Our approach outperforms prior works and sets a new standard for bot detection in social networks.

cs.AI↗

arXiv2023

FineEHR: Refine Clinical Note Representations to Improve Mortality Prediction

Monitoring the health status of patients in the Intensive Care Unit (ICU) is a critical aspect of providing superior care and treatment. The availability of large-scale electronic health records (EHR) provides machine learning models with an abundance of clinical text and vital sign data, enabling them to make highly accurate predictions. Despite the emergence of advanced Natural Language Processing (NLP) algorithms for clinical note analysis, the complex textual structure and noise present in raw clinical data have posed significant challenges. Coarse embedding approaches without domain-specific refinement have limited the accuracy of these algorithms. To address this issue, we propose FINEEHR, a system that utilizes two representation learning techniques, namely metric learning and fine-tuning, to refine clinical note embeddings, while leveraging the intrinsic correlations among different health statuses and note categories. We evaluate the performance of FINEEHR using two metrics, namely Area Under the Curve (AUC) and AUC-PR, on a real-world MIMIC III dataset. Our experimental results demonstrate that both refinement approaches improve prediction accuracy, and their combination yields the best results. Moreover, our proposed method outperforms prior works, with an AUC improvement of over 10%, achieving an average AUC of 96.04% and an average AUC-PR of 96.48% across various classifiers.

cs.AI↗

arXiv2023

BotShape: A Novel Social Bots Detection Approach via Behavioral Patterns

An essential topic in online social network security is how to accurately detect bot accounts and relieve their harmful impacts (e.g., misinformation, rumor, and spam) on genuine users. Based on a real-world data set, we construct behavioral sequences from raw event logs. After extracting critical characteristics from behavioral time series, we observe differences between bots and genuine users and similar patterns among bot accounts. We present a novel social bot detection system BotShape, to automatically catch behavioral sequences and characteristics as features for classifiers to detect bots. We evaluate the detection performance of our system in ground-truth instances, showing an average accuracy of 98.52% and an average f1-score of 96.65% on various types of classifiers. After comparing it with other research, we conclude that BotShape is a novel approach to profiling an account, which could improve performance for most methods by providing significant behavioral features.

cs.SI↗

arXiv2023

Experimental Twin-Field Quantum Key Distribution Over 1000 km Fiber Distance

Quantum key distribution (QKD) aims to generate secure private keys shared by two remote parties. With its security being protected by principles of quantum mechanics, some technology challenges remain towards practical application of QKD. The major one is the distance limit, which is caused by the fact that a quantum signal cannot be amplified while the channel loss is exponential with the distance for photon transmission in optical fiber. Here using the 3-intensity sending-or-not-sending protocol with the actively-odd-parity-pairing method, we demonstrate a fiber-based twin-field QKD over 1002 km. In our experiment, we developed a dual-band phase estimation and ultra-low noise superconducting nanowire single-photon detectors to suppress the system noise to around 0.02 Hz. The secure key rate is $9.53\times10^{-12}$ per pulse through 1002 km fiber in the asymptotic regime, and $8.75\times10^{-12}$ per pulse at 952 km considering the finite size effect. Our work constitutes a critical step towards the future large-scale quantum network.

quant-ph↗

arXiv2023

Non-IID Transfer Learning on Graphs

Transfer learning refers to the transfer of knowledge or information from a relevant source domain to a target domain. However, most existing transfer learning theories and algorithms focus on IID tasks, where the source/target samples are assumed to be independent and identically distributed. Very little effort is devoted to theoretically studying the knowledge transferability on non-IID tasks, e.g., cross-network mining. To bridge the gap, in this paper, we propose rigorous generalization bounds and algorithms for cross-network transfer learning from a source graph to a target graph. The crucial idea is to characterize the cross-network knowledge transferability from the perspective of the Weisfeiler-Lehman graph isomorphism test. To this end, we propose a novel Graph Subtree Discrepancy to measure the graph distribution shift between source and target graphs. Then the generalization error bounds on cross-network transfer learning, including both cross-network node classification and link prediction tasks, can be derived in terms of the source knowledge and the Graph Subtree Discrepancy across domains. This thereby motivates us to propose a generic graph adaptive network (GRADE) to minimize the distribution shift between source and target graphs for cross-network transfer learning. Experimental results verify the effectiveness and efficiency of our GRADE framework on both cross-network node classification and cross-domain recommendation tasks.

cs.LG↗

arXiv2023

EdgeLaaS: Edge Learning as a Service for Knowledge-Centric Connected Healthcare

By introducing networking technologies and services into healthcare infrastructures (e.g., multimodal sensors and smart devices) that are deployed to supervise a person's health condition, the traditional healthcare system is being revolutionized toward knowledge-centric connected healthcare (KCCH), where persons will take their own responsibility for their healthcare in a knowledge-centric way. Due to the volume, velocity, and variety of healthcare supervision data generated by these healthcare infrastructures, an urgent and strategic issue is how to efficiently process a person's healthcare supervision data with the right knowledge of the right guardians (e.g., relatives, nurses, and doctors) at the right time. To solve this issue, the naming and routing criterion of medical knowledge is studied. With this offloaded medical knowledge, we propose an edge learning as a service (EdgeLaaS) framework for KCCH to locally process health supervision data. In this framework, edge learning nodes can help the patient choose better advice from the right guardians in real time when some emergencies occur. Two application cases: 1) fast self-help and 2) mobile help pre-calling are studied. Performance evaluations demonstrate the superiority of KCCH and EdgeLaaS, respectively.

cs.NI↗

arXiv2023

Fabrication Sequence Optimization for Minimizing Distortion in Multi-Axis Additive Manufacturing

Additive manufacturing of metal parts involves phase transformations and high temperature gradients which lead to uneven thermal expansion and contraction, and, consequently, distortion of the fabricated components. The distortion has a great influence on the structural performance and dimensional accuracy, e.g., for assembly. It is therefore of critical importance to model, predict and, ultimately, reduce distortion. In this paper, we present a computational framework for fabrication sequence optimization to minimize distortion in multi-axis additive manufacturing (e.g., robotic wire arc additive manufacturing), in which the fabrication sequence is not limited to planar layers only. We encode the fabrication sequence by a continuous pseudo-time field, and optimize it using gradient-based numerical optimization. To demonstrate this framework, we adopt a computationally tractable yet reasonably accurate model to mimic the material shrinkage in metal additive manufacturing and thus to predict the distortion of the fabricated components. Numerical studies show that optimized curved layers can reduce distortion by orders of magnitude as compared to their planar counterparts.

cs.CE↗