arXiv subjects

Yan Liu

Publications and source records attributed to Yan Liu.

At least 379 records · Page 21Linked to original sources

arXiv2020

PSCS: A Path-based Neural Model for Semantic Code Search

To obtain code snippets for reuse, programmers prefer to search for related documents, e.g., blogs or Q&A, instead of code itself. The major reason is due to the semantic diversity and mismatch between queries and code snippets. Deep learning models have been proposed to address this challenge. Compared with approaches using information retrieval techniques, deep learning models do not suffer from the information loss caused by refining user intention into keywords. However, the performance of previous works is not satisfactory because they ignore the importance of code structure. When the semantics of code (e.g., identifier names, APIs) are ambiguous, code structure may be the only feature for the model to utilize. In that case, previous works relearn the structural information from lexical tokens of code, which is extremely difficult for a model without any domain knowledge. In this work, we propose PSCS, a path-based neural model for semantic code search. Our model encodes both the semantics and structures of code represented by AST paths. We train and evaluate our model over 330k-19k query-function pairs, respectively. The evaluation results demonstrate that PSCS achieves a SuccessRate of 47.6% and a Mean Reciprocal Rank (MRR) of 30.4% when considering the top-10 results with a match. The proposed approach significantly outperforms both DeepCS, the first approach that applies deep learning to code search task, and CARLCS, a state-of-the-art approach that introduces a co-attentive representation learning model on the basis of DeepCS. The importance of code structure is demonstrated with an ablation study on code features, which enlightens model design for further studies.

cs.SE↗

arXiv2020

Network Intrusion Detection Using Wrapper-based Decision Tree for Feature Selection

One of the key challenges of machine learning (ML) based intrusion detection system (IDS) is the expensive computational complexity which is largely due to redundant, incomplete, and irrelevant features contain in the IDS datasets. To overcome such challenge and ensure building an efficient and more accurate IDS models, many researchers utilize preprocessing techniques such as normalization and feature selection in a hybrid modeling approach. In this work, we propose a hybrid IDS modeling approach with an algorithm for feature selection (FS) and another for building an IDS. The FS algorithm is a wrapper-based with a decision tree as the feature evaluator. The propose FS method is used in combination with some selected ML algorithms to build IDS models using the UNSW-NB15 dataset. Some IDS models are built as a baseline in a single modeling approach using the full features of the dataset. We evaluate the effectiveness of our propose method by comparing it with the baseline models and also with state-of-the-art works. Our method achieves the best DR of 97.95% and shown to be quite effective in comparison to state-of-the-art works. We, therefore, recommend its usage especially in IDS modeling with the UNSW-NB15 dataset.

cs.CR↗

arXiv2020

Network Inference from a Mixture of Diffusion Models for Fake News Mitigation

The dissemination of fake news intended to deceive people, influence public opinion and manipulate social outcomes, has become a pressing problem on social media. Moreover, information sharing on social media facilitates diffusion of viral information cascades. In this work, we focus on understanding and leveraging diffusion dynamics of false and legitimate contents in order to facilitate network interventions for fake news mitigation. We analyze real-world Twitter datasets comprising fake and true news cascades, to understand differences in diffusion dynamics and user behaviours with regards to fake and true contents. Based on the analysis, we model the diffusion as a mixture of Independent Cascade models (MIC) with parameters $θ_T, θ_F$ over the social network graph; and derive unsupervised inference techniques for parameter estimation of the diffusion mixture model from observed, unlabeled cascades. Users influential in the propagation of true and fake contents are identified using the inferred diffusion dynamics. Characteristics of the identified influential users reveal positive correlation between influential users identified for fake news and their relative appearance in fake news cascades. Identified influential users tend to be related to topics of more viral information cascades than less viral ones; and identified fake news influential users have relatively fewer counts of direct followers, compared to the true news influential users. Intervention analysis on nodes and edges demonstrates capacity of the inferred diffusion dynamics in supporting network interventions for mitigation.

cs.SI↗

arXiv2020

MAGIC: Manifold and Graph Integrative Convolutional Network for Low-Dose CT Reconstruction

Low-dose computed tomography (LDCT) scans, which can effectively alleviate the radiation problem, will degrade the imaging quality. In this paper, we propose a novel LDCT reconstruction network that unrolls the iterative scheme and performs in both image and manifold spaces. Because patch manifolds of medical images have low-dimensional structures, we can build graphs from the manifolds. Then, we simultaneously leverage the spatial convolution to extract the local pixel-level features from the images and incorporate the graph convolution to analyze the nonlocal topological features in manifold space. The experiments show that our proposed method outperforms both the quantitative and qualitative aspects of state-of-the-art methods. In addition, aided by a projection loss component, our proposed method also demonstrates superior performance for semi-supervised learning. The network can remove most noise while maintaining the details of only 10% (40 slices) of the training data labeled.

eess.IV↗

arXiv2020

Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks

Most existing crowd counting systems rely on the availability of the object location annotation which can be expensive to obtain. To reduce the annotation cost, one attractive solution is to leverage a large number of unlabeled images to build a crowd counting model in semi-supervised fashion. This paper tackles the semi-supervised crowd counting problem from the perspective of feature learning. Our key idea is to leverage the unlabeled images to train a generic feature extractor rather than the entire network of a crowd counter. The rationale of this design is that learning the feature extractor can be more reliable and robust towards the inevitable noisy supervision generated from the unlabeled data. Also, on top of a good feature extractor, it is possible to build a density map regressor with much fewer density map annotations. Specifically, we proposed a novel semi-supervised crowd counting method which is built upon two innovative components: (1) a set of inter-related binary segmentation tasks are derived from the original density map regression task as the surrogate prediction target; (2) the surrogate target predictors are learned from both labeled and unlabeled data by utilizing a proposed self-training scheme which fully exploits the underlying constraints of these binary segmentation tasks. Through experiments, we show that the proposed method is superior over the existing semisupervised crowd counting method and other representative baselines.

cs.CV↗

arXiv2020

Analyzing Grant-Free Access for URLLC Service

5G New Radio (NR) is expected to support new ultra-reliable low-latency communication (URLLC) service targeting at supporting the small packets transmissions with very stringent latency and reliability requirements. Current Long Term Evolution (LTE) system has been designed based on grantbased (GB) (i.e., dynamic grant) random access, which can hardly support the URLLC requirements. Grant-free (GF) (i.e., configured grant) access is proposed as a feasible and promising technology to meet such requirements, especially for uplink transmissions, which effectively saves the time of requesting/waiting for a grant. While some basic GF access features have been proposed and standardized in NR Release-15, there is still much space to improve. Being proposed as 3GPP study items, three GF access schemes with Hybrid Automatic Repeat reQuest (HARQ) retransmissions including Reactive, K-repetition, and Proactive, are analyzed in this paper. Specifically, we present a spatiotemporal analytical framework for the contention-based GF access analysis. Based on this framework, we define the latent access failure probability to characterize URLLC reliability and latency performances. We propose a tractable approach to derive and analyze the latent access failure probability of the typical UE under three GF HARQ schemes. Our results show that under shorter latency constraints, the Proactive scheme provides the lowest latent access failure probability, whereas, under longer latency constraints, the K-repetition scheme achieves the lowest latent access failure probability, which depends on K. If K is overestimated, the Proactive scheme provides lower latent access failure probability than the K-repetition scheme.

eess.SP↗

arXiv2020

Noise-Powered Disentangled Representation for Unsupervised Speckle Reduction of Optical Coherence Tomography Images

Due to its noninvasive character, optical coherence tomography (OCT) has become a popular diagnostic method in clinical settings. However, the low-coherence interferometric imaging procedure is inevitably contaminated by heavy speckle noise, which impairs both visual quality and diagnosis of various ocular diseases. Although deep learning has been applied for image denoising and achieved promising results, the lack of well-registered clean and noisy image pairs makes it impractical for supervised learning-based approaches to achieve satisfactory OCT image denoising results. In this paper, we propose an unsupervised OCT image speckle reduction algorithm that does not rely on well-registered image pairs. Specifically, by employing the ideas of disentangled representation and generative adversarial network, the proposed method first disentangles the noisy image into content and noise spaces by corresponding encoders. Then, the generator is used to predict the denoised OCT image with the extracted content features. In addition, the noise patches cropped from the noisy image are utilized to facilitate more accurate disentanglement. Extensive experiments have been conducted, and the results suggest that our proposed method is superior to the classic methods and demonstrates competitive performance to several recently proposed learning-based approaches in both quantitative and qualitative aspects.

eess.IV↗

arXiv2020

Gallai-Ramsey numbers for monochromatic $K_4^{+}$ or $K_{3}$

A Gallai $k$-coloring is a $k$-edge coloring of a complete graph in which there are no rainbow triangles. For two given graphs $H, G$ and two positive integers $k,s$ with that $s\leq k$, the $k$-colored Gallai-Ramsey number $gr_{k}(K_{3}: s\cdot H,~ (k-s)\cdot G)$ is the minimum integer $n$ such that every Gallai $k$-colored $K_{n}$ contains a monochromatic copy of $H$ colored by one of the first $s$ colors or a monochromatic copy of $G$ colored by one of the remaining $k-s$ colors. In this paper, we determine the value of Gallai-Ramsey number in the case that $H=K_{4}^{+}$ and $G=K_{3}$. Thus the Gallai-Ramsey number $gr_{k}(K_{3}: K_{4}^{+})$ is obtained.

math.CO↗

arXiv2020

Decomposing Word Embedding with the Capsule Network

Word sense disambiguation tries to learn the appropriate sense of an ambiguous word in a given context. The existing pre-trained language methods and the methods based on multi-embeddings of word did not explore the power of the unsupervised word embedding sufficiently. In this paper, we discuss a capsule network-based approach, taking advantage of capsule's potential for recognizing highly overlapping features and dealing with segmentation. We propose a Capsule network-based method to Decompose the unsupervised word Embedding of an ambiguous word into context specific Sense embedding, called CapsDecE2S. In this approach, the unsupervised ambiguous embedding is fed into capsule network to produce its multiple morpheme-like vectors, which are defined as the basic semantic language units of meaning. With attention operations, CapsDecE2S integrates the word context to reconstruct the multiple morpheme-like vectors into the context-specific sense embedding. To train CapsDecE2S, we propose a sense matching training method. In this method, we convert the sense learning into a binary classification that explicitly learns the relation between senses by the label of matching and non-matching. The CapsDecE2S was experimentally evaluated on two sense learning tasks, i.e., word in context and word sense disambiguation. Results on two public corpora Word-in-Context and English all-words Word Sense Disambiguation show that, the CapsDecE2S model achieves the new state-of-the-art for the word in context and word sense disambiguation tasks.

cs.CL↗

arXiv2020

Human Activity Recognition based on Dynamic Spatio-Temporal Relations

Human activity, which usually consists of several actions, generally covers interactions among persons and or objects. In particular, human actions involve certain spatial and temporal relationships, are the components of more complicated activity, and evolve dynamically over time. Therefore, the description of a single human action and the modeling of the evolution of successive human actions are two major issues in human activity recognition. In this paper, we develop a method for human activity recognition that tackles these two issues. In the proposed method, an activity is divided into several successive actions represented by spatio temporal patterns, and the evolution of these actions are captured by a sequential model. A refined comprehensive spatio temporal graph is utilized to represent a single action, which is a qualitative representation of a human action incorporating both the spatial and temporal relations of the participant objects. Next, a discrete hidden Markov model is applied to model the evolution of action sequences. Moreover, a fully automatic partition method is proposed to divide a long-term human activity video into several human actions based on variational objects and qualitative spatial relations. Finally, a hierarchical decomposition of the human body is introduced to obtain a discriminative representation for a single action. Experimental results on the Cornell Activity Dataset demonstrate the efficiency and effectiveness of the proposed approach, which will enable long videos of human activity to be better recognized.

cs.CV↗

arXiv2020

How does this interaction affect me? Interpretable attribution for feature interactions

Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence between features that jointly impact predictions. There are a number of methods that extract feature interactions in prediction models; however, the methods that assign attributions to interactions are either uninterpretable, model-specific, or non-axiomatic. We propose an interaction attribution and detection framework called Archipelago which addresses these problems and is also scalable in real-world settings. Our experiments on standard annotation labels indicate our approach provides significantly more interpretable explanations than comparable methods, which is important for analyzing the impact of interactions on predictions. We also provide accompanying visualizations of our approach that give new insights into deep neural networks.

stat.ML↗

arXiv2020

Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection

Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable. In this work, we propose a method to both interpret and augment the predictions of black-box recommender systems. In particular, we propose to interpret feature interactions from a source recommender model and explicitly encode these interactions in a target recommender model, where both source and target models are black-boxes. By not assuming the structure of the recommender system, our approach can be used in general settings. In our experiments, we focus on a prominent use of machine learning recommendation: ad-click prediction. We found that our interaction interpretations are both informative and predictive, e.g., significantly outperforming existing recommender models. What's more, the same approach to interpret interactions can provide new insights into domains even beyond recommendation, such as text and image classification.

stat.ML↗

arXiv2020

False (and Missed) Discoveries in Financial Economics

Multiple testing plagues many important questions in finance such as fund and factor selection. We propose a new way to calibrate both Type I and Type II errors. Next, using a double-bootstrap method, we establish a t-statistic hurdle that is associated with a specific false discovery rate (e.g., 5%). We also establish a hurdle that is associated with a certain acceptable ratio of misses to false discoveries (Type II error scaled by Type I error), which effectively allows for differential costs of the two types of mistakes. Evaluating current methods, we find that they lack power to detect outperforming managers.

stat.ME↗

arXiv2020

Req2Lib: A Semantic Neural Model for Software Library Recommendation

Third-party libraries are crucial to the development of software projects. To get suitable libraries, developers need to search through millions of libraries by filtering, evaluating, and comparing. The vast number of libraries places a barrier for programmers to locate appropriate ones. To help developers, researchers have proposed automated approaches to recommend libraries based on library usage pattern. However, these prior studies can not sufficiently match user requirements and suffer from cold-start problem. In this work, we would like to make recommendations based on requirement descriptions to avoid these problems. To this end, we propose a novel neural approach called Req2Lib which recommends libraries given descriptions of the project requirement. We use a Sequence-to-Sequence model to learn the library linked-usage information and semantic information of requirement descriptions in natural language. Besides, we apply a domain-specific pre-trained word2vec model for word embedding, which is trained over textual corpus from Stack Overflow posts. In the experiment, we train and evaluate the model with data from 5,625 java projects. Our preliminary evaluation demonstrates that Req2Lib can recommend libraries accurately.

cs.SE↗

arXiv2020

MD-Recon-Net: A Parallel Dual-Domain Convolutional Neural Network for Compressed Sensing MRI

Compressed sensing magnetic resonance imaging (CS-MRI) is a theoretical framework that can accurately reconstruct images from undersampled k-space data with a much lower sampling rate than the one set by the classical Nyquist-Shannon sampling theorem. Therefore, CS-MRI can efficiently accelerate acquisition time and relieve the psychological burden on patients while maintaining high imaging quality. The problems with traditional CS-MRI reconstruction are solved by iterative numerical solvers, which usually suffer from expensive computational cost and the lack of accurate handcrafted priori. In this paper, inspired by deep learning's (DL's) fast inference and excellent end-to-end performance, we propose a novel cascaded convolutional neural network called MD-Recon-Net to facilitate fast and accurate MRI reconstruction. Especially, different from existing DL-based methods, which operate on single domain data or both domains in a certain order, our proposed MD-Recon-Net contains two parallel and interactive branches that simultaneously perform on k-space and spatial-domain data, exploring the latent relationship between k-space and the spatial domain. The simulated experimental results show that the proposed method not only achieves competitive visual effects to several state-of-the-art methods, but also outperforms other DL-based methods in terms of model scale and computational cost.

physics.med-ph↗

arXiv2020

Subterahertz spin pumping from an insulating antiferromagnet

Spin-transfer torque and spin Hall effects combined with their reciprocal phenomena, spin-pumping and inverse spin Hall (ISHE) effects, enable the reading and control of magnetic moments in spintronics. The direct observation of these effects remains elusive in antiferromagnetic-based devices. We report sub-terahertz spin-pumping at the interface of a uniaxial insulating antiferromagnet MnF2 and platinum. The measured ISHE voltage arising from spin-charge conversion in the platinum layer depends on the chirality of the dynamical modes of the antiferromagnet, which is selectively excited and modulated by the handedness of the circularly polarized sub-THz irradiation. Our results open the door to the controlled generation of coherent pure spin currents at THz frequencies.

cond-mat.mtrl-sci↗

arXiv2020

Effective Human Activity Recognition Based on Small Datasets

Most recent work on vision-based human activity recognition (HAR) focuses on designing complex deep learning models for the task. In so doing, there is a requirement for large datasets to be collected. As acquiring and processing large training datasets are usually very expensive, the problem of how dataset size can be reduced without affecting recognition accuracy has to be tackled. To do so, we propose a HAR method that consists of three steps: (i) data transformation involving the generation of new features based on transforming of raw data, (ii) feature extraction involving the learning of a classifier based on the AdaBoost algorithm and the use of training data consisting of the transformed features, and (iii) parameter determination and pattern recognition involving the determination of parameters based on the features generated in (ii) and the use of the parameters as training data for deep learning algorithms to be used to recognize human activities. Compared to existing approaches, this proposed approach has the advantageous characteristics that it is simple and robust. The proposed approach has been tested with a number of experiments performed on a relatively small real dataset. The experimental results indicate that using the proposed method, human activities can be more accurately recognized even with smaller training data size.

cs.CV↗

arXiv2020

Skeleton Focused Human Activity Recognition in RGB Video

The data-driven approach that learns an optimal representation of vision features like skeleton frames or RGB videos is currently a dominant paradigm for activity recognition. While great improvements have been achieved from existing single modal approaches with increasingly larger datasets, the fusion of various data modalities at the feature level has seldom been attempted. In this paper, we propose a multimodal feature fusion model that utilizes both skeleton and RGB modalities to infer human activity. The objective is to improve the activity recognition accuracy by effectively utilizing the mutual complemental information among different data modalities. For the skeleton modality, we propose to use a graph convolutional subnetwork to learn the skeleton representation. Whereas for the RGB modality, we will use the spatial-temporal region of interest from RGB videos and take the attention features from the skeleton modality to guide the learning process. The model could be either individually or uniformly trained by the back-propagation algorithm in an end-to-end manner. The experimental results for the NTU-RGB+D and Northwestern-UCLA Multiview datasets achieved state-of-the-art performance, which indicates that the proposed skeleton-driven attention mechanism for the RGB modality increases the mutual communication between different data modalities and brings more discriminative features for inferring human activities.

cs.CV↗