arXiv subjects

Ling Huang

Publications and source records attributed to Ling Huang.

At least 55 records · Page 3Linked to original sources

arXiv2021

Belief function-based semi-supervised learning for brain tumor segmentation

Precise segmentation of a lesion area is important for optimizing its treatment. Deep learning makes it possible to detect and segment a lesion field using annotated data. However, obtaining precisely annotated data is very challenging in the medical domain. Moreover, labeling uncertainty and imprecision make segmentation results unreliable. In this paper, we address the uncertain boundary problem by a new evidential neural network with an information fusion strategy, and the scarcity of annotated data by semi-supervised learning. Experimental results show that our proposal has better performance than state-of-the-art methods.

cs.CV↗

arXiv2021

Covid-19 classification with deep neural network and belief functions

Computed tomography (CT) image provides useful information for radiologists to diagnose Covid-19. However, visual analysis of CT scans is time-consuming. Thus, it is necessary to develop algorithms for automatic Covid-19 detection from CT images. In this paper, we propose a belief function-based convolutional neural network with semi-supervised training to detect Covid-19 cases. Our method first extracts deep features, maps them into belief degree maps and makes the final classification decision. Our results are more reliable and explainable than those of traditional deep learning-based classification models. Experimental results show that our approach is able to achieve a good performance with an accuracy of 0.81, an F1 of 0.812 and an AUC of 0.875.

eess.IV↗

arXiv2020

Modeling Heterogeneous Statistical Patterns in High-dimensional Data by Adversarial Distributions: An Unsupervised Generative Framework

Since the label collecting is prohibitive and time-consuming, unsupervised methods are preferred in applications such as fraud detection. Meanwhile, such applications usually require modeling the intrinsic clusters in high-dimensional data, which usually displays heterogeneous statistical patterns as the patterns of different clusters may appear in different dimensions. Existing methods propose to model the data clusters on selected dimensions, yet globally omitting any dimension may damage the pattern of certain clusters. To address the above issues, we propose a novel unsupervised generative framework called FIRD, which utilizes adversarial distributions to fit and disentangle the heterogeneous statistical patterns. When applying to discrete spaces, FIRD effectively distinguishes the synchronized fraudsters from normal users. Besides, FIRD also provides superior performance on anomaly detection datasets compared with SOTA anomaly detection methods (over 5% average AUC improvement). The significant experiment results on various datasets verify that the proposed method can better model the heterogeneous statistical patterns in high-dimensional data and benefit downstream applications.

cs.LG↗

arXiv2020

An extended $R^{(2)}_{Ψ_m}(ΔS_2)$ correlator for detecting and characterizing the Chiral Magnetic Wave

The extended $R^{(2)}_{Ψ_{m}}(ΔS_{2})$ correlator is presented and examined for its efficacy to detect and characterize the quadrupole charge separation ($ΔS_{2}$) associated with the purported Chiral Magnetic Wave (CMW) produced in heavy-ion collisions. Sensitivity tests involving varying degrees of proxy CMW signals injected into events simulated with the Multi-Phase Transport Model (AMPT), show that the $R^{(2)}_{Ψ_{m}}(ΔS_{2})$ correlator provides discernible responses for the background- and CMW-driven charge separation. This distinction could aid identification of the CMW via measurements of the $R^{(2)}_{Ψ_{2}}(ΔS_{2})$ and $R^{(2)}_{Ψ_{3}}(ΔS_{2})$ correlators, relative to the second- ($Ψ_2$) and third-order ($Ψ_3$) event planes. The tests also indicate a level of sensitivity that would allow for robust experimental characterization of the CMW signal.

nucl-ex↗

arXiv2019

Sensitivity analysis of the chiral magnetic effect observables using a multiphase transport model

Because the traditional observable of charge-dependent azimuthal correlator $γ$ contains both contributions from the chiral magnetic effect (CME) and its background, a new observable of $R_{Ψ_{m}}$ has been recently proposed which is expected to be able to distinguish the CME from the background. In this study, we apply two methods to calculate $R_{Ψ_{m}}$ using a multiphase transport model without or with introducing a percentage of CME-induced charge separation. We demonstrate that the shape of final $R_{Ψ_{2}}$ distribution is flat for the case without the CME, but concave for that with an amount of the CME, because the initial CME signal survives from strong final state interactions. By comparing the responses of $R_{Ψ_{2}}$ and $γ$ to the strength of the initial CME, we observe that two observables show different nonlinear sensitivities to the CME. We find that the shape of $R_{Ψ_{2}}$ has an advantage in measuring a small amount of the CME, although it requires large event statistics.

nucl-th↗

arXiv2019

DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction

Pattern-based labeling methods have achieved promising results in alleviating the inevitable labeling noises of distantly supervised neural relation extraction. However, these methods require significant expert labor to write relation-specific patterns, which makes them too sophisticated to generalize quickly.To ease the labor-intensive workload of pattern writing and enable the quick generalization to new relation types, we propose a neural pattern diagnosis framework, DIAG-NRE, that can automatically summarize and refine high-quality relational patterns from noise data with human experts in the loop. To demonstrate the effectiveness of DIAG-NRE, we apply it to two real-world datasets and present both significant and interpretable improvements over state-of-the-art methods.

cs.CL↗

arXiv2019

EdMot: An Edge Enhancement Approach for Motif-aware Community Detection

Network community detection is a hot research topic in network analysis. Although many methods have been proposed for community detection, most of them only take into consideration the lower-order structure of the network at the level of individual nodes and edges. Thus, they fail to capture the higher-order characteristics at the level of small dense subgraph patterns, e.g., motifs. Recently, some higher-order methods have been developed but they typically focus on the motif-based hypergraph which is assumed to be a connected graph. However, such assumption cannot be ensured in some real-world networks. In particular, the hypergraph may become fragmented. That is, it may consist of a large number of connected components and isolated nodes, despite the fact that the original network is a connected graph. Therefore, the existing higher-order methods would suffer seriously from the above fragmentation issue, since in these approaches, nodes without connection in hypergraph can't be grouped together even if they belong to the same community. To address the above fragmentation issue, we propose an Edge enhancement approach for Motif-aware community detection (EdMot). The main idea is as follows. Firstly, a motif-based hypergraph is constructed and the top K largest connected components in the hypergraph are partitioned into modules. Afterwards, the connectivity structure within each module is strengthened by constructing an edge set to derive a clique from each module. Based on the new edge set, the original connectivity structure of the input network is enhanced to generate a rewired network, whereby the motif-based higher-order structure is leveraged and the hypergraph fragmentation issue is well addressed. Finally, the rewired network is partitioned to obtain the higher-order community structure.

cs.SI↗

arXiv2019

DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System

In general, recommendation can be viewed as a matching problem, i.e., match proper items for proper users. However, due to the huge semantic gap between users and items, it's almost impossible to directly match users and items in their initial representation spaces. To solve this problem, many methods have been studied, which can be generally categorized into two types, i.e., representation learning-based CF methods and matching function learning-based CF methods. Representation learning-based CF methods try to map users and items into a common representation space. In this case, the higher similarity between a user and an item in that space implies they match better. Matching function learning-based CF methods try to directly learn the complex matching function that maps user-item pairs to matching scores. Although both methods are well developed, they suffer from two fundamental flaws, i.e., the limited expressiveness of dot product and the weakness in capturing low-rank relations respectively. To this end, we propose a general framework named DeepCF, short for Deep Collaborative Filtering, to combine the strengths of the two types of methods and overcome such flaws. Extensive experiments on four publicly available datasets demonstrate the effectiveness of the proposed DeepCF framework.

cs.LG↗

arXiv2018

BadLink: Combining Graph and Information-Theoretical Features for Online Fraud Group Detection

Frauds severely hurt many kinds of Internet businesses. Group-based fraud detection is a popular methodology to catch fraudsters who unavoidably exhibit synchronized behaviors. We combine both graph-based features (e.g. cluster density) and information-theoretical features (e.g. probability for the similarity) of fraud groups into two intuitive metrics. Based on these metrics, we build an extensible fraud detection framework, BadLink, to support multimodal datasets with different data types and distributions in a scalable way. Experiments on real production workload, as well as extensive comparison with existing solutions demonstrate the state-of-the-art performance of BadLink, even with sophisticated camouflage traffic.

cs.CR↗

arXiv2018

Investigating the quark flavor dependence of the chiral magnetic effect with a multiphase transport model

Because the properties of the QCD phase transition and the chiral magnetic effect (CME) depend on the number of quark flavors ($N_{f}$) and quark mass, relativistic heavy-ion collisions provide a natural environment to investigate the flavor features if quark deconfinement occurs. We introduce an initial two-flavor or three-flavor dipole charge separation into a multiphase transport (AMPT) model to investigate the flavor dependence of the CME. By taking advantage of the recent ALICE data of charge azimuthal correlations with identified hadrons, we attempt to disentangle two-flavor and three-flavor CME scenarios in Pb+Pb collisions at 2.76 TeV. We find that the experimental data show a certain potential to distinguish the two scenarios, therefore we further suggest to collect more data to clarify the possible flavor dependence in future experiments.

nucl-th↗

arXiv2016

Vertical dynamics of a horizontally-oscillating active object in a 2D granular medium

We use a DEM simulation and analytical considerations to study the dynamics of a self-energised object, modelled as a disc, oscillating horizontally within a two-dimesional bed of denser and smaller particles. We find that, for given material parameters, the immersed object (IO) may rise, sink or not change depth, depending on the oscillation amplitude and frequency, as well as on the initial depth. With time, the IO settles at a specific depth that depends on the oscillation parameters. We construct a phase diagram of this behaviour in the oscillation frequency and velocity amplitude variable space. We explain the observed rich behaviour by two competing effects: climbing on particles, which fill voids opening under the disc, and sinking due to bed fluidisation. We present a cavity model that allows us to derive analytically general results, which agree very well with the observations and explain quantitatively the phase diagram. Our specific analytical results are the following. (i) Derivation of a critical frequency, $f_c$, above which the IO cannot float up against gravity. We show that this frequency depends only on the gravitational acceleration and the IO size. (ii) Derivation of a minimal amplitude, $A_{min}$, below which the IO cannot rise even if the frequency is below $f_c$. We show that this amplitude also depends only on the gravitational acceleration and the IO size. (iii) Derivation of a critical value, $g_c$, of the IO's acceleration amplitude, below which the IO cannot sink. We show that the value of $g_c$ depends on the characteristics of both the IO and the granular bed,as well as on the initial IO's depth.

cond-mat.soft↗

arXiv2016

Reviewer Integration and Performance Measurement for Malware Detection

We present and evaluate a large-scale malware detection system integrating machine learning with expert reviewers, treating reviewers as a limited labeling resource. We demonstrate that even in small numbers, reviewers can vastly improve the system's ability to keep pace with evolving threats. We conduct our evaluation on a sample of VirusTotal submissions spanning 2.5 years and containing 1.1 million binaries with 778GB of raw feature data. Without reviewer assistance, we achieve 72% detection at a 0.5% false positive rate, performing comparable to the best vendors on VirusTotal. Given a budget of 80 accurate reviews daily, we improve detection to 89% and are able to detect 42% of malicious binaries undetected upon initial submission to VirusTotal. Additionally, we identify a previously unnoticed temporal inconsistency in the labeling of training datasets. We compare the impact of training labels obtained at the same time training data is first seen with training labels obtained months later. We find that using training labels obtained well after samples appear, and thus unavailable in practice for current training data, inflates measured detection by almost 20 percentage points. We release our cluster-based implementation, as well as a list of all hashes in our evaluation and 3% of our entire dataset.

cs.CR↗

arXiv2016

EMMA: A New Platform to Evaluate Hardware-based Mobile Malware Analyses

Hardware-based malware detectors (HMDs) are a key emerging technology to build trustworthy computing platforms, especially mobile platforms. Quantifying the efficacy of HMDs against malicious adversaries is thus an important problem. The challenge lies in that real-world malware typically adapts to defenses, evades being run in experimental settings, and hides behind benign applications. Thus, realizing the potential of HMDs as a line of defense - that has a small and battery-efficient code base - requires a rigorous foundation for evaluating HMDs. To this end, we introduce EMMA - a platform to evaluate the efficacy of HMDs for mobile platforms. EMMA deconstructs malware into atomic, orthogonal actions and introduces a systematic way of pitting different HMDs against a diverse subset of malware hidden inside benign applications. EMMA drives both malware and benign programs with real user-inputs to yield an HMD's effective operating range - i.e., the malware actions a particular HMD is capable of detecting. We show that small atomic actions, such as stealing a Contact or SMS, have surprisingly large hardware footprints, and use this insight to design HMD algorithms that are less intrusive than prior work and yet perform 24.7% better. Finally, EMMA brings up a surprising new result - obfuscation techniques used by malware to evade static analyses makes them more detectable using HMDs.

cs.CR↗

arXiv2014

I Know Why You Went to the Clinic: Risks and Realization of HTTPS Traffic Analysis

Revelations of large scale electronic surveillance and data mining by governments and corporations have fueled increased adoption of HTTPS. We present a traffic analysis attack against over 6000 webpages spanning the HTTPS deployments of 10 widely used, industry-leading websites in areas such as healthcare, finance, legal services and streaming video. Our attack identifies individual pages in the same website with 89% accuracy, exposing personal details including medical conditions, financial and legal affairs and sexual orientation. We examine evaluation methodology and reveal accuracy variations as large as 18% caused by assumptions affecting caching and cookies. We present a novel defense reducing attack accuracy to 27% with a 9% traffic increase, and demonstrate significantly increased effectiveness of prior defenses in our evaluation context, inclusive of enabled caching, user-specific cookies and pages within the same website.

cs.CR↗

arXiv2012

Evolution of Social-Attribute Networks: Measurements, Modeling, and Implications using Google+

Understanding social network structure and evolution has important implications for many aspects of network and system design including provisioning, bootstrapping trust and reputation systems via social networks, and defenses against Sybil attacks. Several recent results suggest that augmenting the social network structure with user attributes (e.g., location, employer, communities of interest) can provide a more fine-grained understanding of social networks. However, there have been few studies to provide a systematic understanding of these effects at scale. We bridge this gap using a unique dataset collected as the Google+ social network grew over time since its release in late June 2011. We observe novel phenomena with respect to both standard social network metrics and new attribute-related metrics (that we define). We also observe interesting evolutionary patterns as Google+ went from a bootstrap phase to a steady invitation-only stage before a public release. Based on our empirical observations, we develop a new generative model to jointly reproduce the social structure and the node attributes. Using theoretical analysis and empirical evaluations, we show that our model can accurately reproduce the social and attribute structure of real social networks. We also demonstrate that our model provides more accurate predictions for practical application contexts.

cs.SI↗

arXiv2012

Jointly Predicting Links and Inferring Attributes using a Social-Attribute Network (SAN)

The effects of social influence and homophily suggest that both network structure and node attribute information should inform the tasks of link prediction and node attribute inference. Recently, Yin et al. proposed Social-Attribute Network (SAN), an attribute-augmented social network, to integrate network structure and node attributes to perform both link prediction and attribute inference. They focused on generalizing the random walk with restart algorithm to the SAN framework and showed improved performance. In this paper, we extend the SAN framework with several leading supervised and unsupervised link prediction algorithms and demonstrate performance improvement for each algorithm on both link prediction and attribute inference. Moreover, we make the novel observation that attribute inference can help inform link prediction, i.e., link prediction accuracy is further improved by first inferring missing attributes. We comprehensively evaluate these algorithms and compare them with other existing algorithms using a novel, large-scale Google+ dataset, which we make publicly available.

cs.SI↗

arXiv2012

Online Semi-Supervised Learning on Quantized Graphs

In this paper, we tackle the problem of online semi-supervised learning (SSL). When data arrive in a stream, the dual problems of computation and data storage arise for any SSL method. We propose a fast approximate online SSL algorithm that solves for the harmonic solution on an approximate graph. We show, both empirically and theoretically, that good behavior can be achieved by collapsing nearby points into a set of local "representative points" that minimize distortion. Moreover, we regularize the harmonic solution to achieve better stability properties. We apply our algorithm to face recognition and optical character recognition applications to show that we can take advantage of the manifold structure to outperform the previous methods. Unlike previous heuristic approaches, we show that our method yields provable performance bounds.

cs.LG↗

arXiv2011

An Analysis of the Convergence of Graph Laplacians

Existing approaches to analyzing the asymptotics of graph Laplacians typically assume a well-behaved kernel function with smoothness assumptions. We remove the smoothness assumption and generalize the analysis of graph Laplacians to include previously unstudied graphs including kNN graphs. We also introduce a kernel-free framework to analyze graph constructions with shrinking neighborhoods in general and apply it to analyze locally linear embedding (LLE). We also describe how for a given limiting Laplacian operator desirable properties such as a convergent spectrum and sparseness can be achieved choosing the appropriate graph construction.

stat.ML↗