Searcharxiv⌕ Search

arXiv subjects

Haiyang Wang

Publications and source records attributed to Haiyang Wang.

68 records · Page 4Linked to original sources
arXiv2021

Drug-Target Interaction Prediction with Graph Attention networks

Motivation: Predicting Drug-Target Interaction (DTI) is a well-studied topic in bioinformatics due to its relevance in the fields of proteomics and pharmaceutical research. Although many machine learning methods have been successfully applied in this task, few of them aim at leveraging the inherent heterogeneous graph structure in the DTI network to address the challenge. For better learning and interpreting the DTI topological structure and the similarity, it is desirable to have methods specifically for predicting interactions from the graph structure. Results: We present an end-to-end framework, DTI-GAT (Drug-Target Interaction prediction with Graph Attention networks) for DTI predictions. DTI-GAT incorporates a deep neural network architecture that operates on graph-structured data with the attention mechanism, which leverages both the interaction patterns and the features of drug and protein sequences. DTI-GAT facilitates the interpretation of the DTI topological structure by assigning different attention weights to each node with the self-attention mechanism. Experimental evaluations show that DTI-GAT outperforms various state-of-the-art systems on the binary DTI prediction problem. Moreover, the independent study results further demonstrate that our model can be generalized better than other conventional methods. Availability: The source code and all datasets are available at https://github.com/Haiyang-W/DTI-GRAPH

q-bio.QM↗
arXiv2021

Integer Dynamics

Let $b \geq 2$ be an integer, and write the base $b$ expansion of any non-negative integer $n$ as $n=x_0+x_1b+\dots+ x_{d}b^{d}$, with $x_d>0$ and $ 0 \leq x_i < b$ for $i=0,\dots,d$. Let $ϕ(x)$ denote an integer polynomial such that $ϕ(n) >0$ for all $n>0$. Consider the map $S_{ϕ,b}: {\mathbb Z}_{\geq 0} \to {\mathbb Z}_{\geq 0}$, with $ S_{ϕ,b}(n) := ϕ(x_0)+ \dots + ϕ(x_d)$. It is known that the orbit set $\{n,S_{ϕ,b}(n), S_{ϕ,b}(S_{ϕ,b}(n)), \dots \}$ is finite for all $n>0$. Each orbit contains a finite cycle, and for a given $b$, the union of such cycles over all orbit sets is finite. Fix now an integer $\ell\geq 1$ and let $ϕ(x)=x^2$. We show that the set of bases $b\geq 2$ which have at least one cycle of length $\ell$ always contains an arithmetic progression and thus has positive lower density. We also show that a 1978 conjecture of Hasse and Prichett on the set of bases with exactly two cycles needs to be modified, raising the possibility that this set might not be finite.

math.NT↗
arXiv2021

Anomaly Detection of Time Series with Smoothness-Inducing Sequential Variational Auto-Encoder

Deep generative models have demonstrated their effectiveness in learning latent representation and modeling complex dependencies of time series. In this paper, we present a Smoothness-Inducing Sequential Variational Auto-Encoder (SISVAE) model for robust estimation and anomaly detection of multi-dimensional time series. Our model is based on Variational Auto-Encoder (VAE), and its backbone is fulfilled by a Recurrent Neural Network to capture latent temporal structures of time series for both generative model and inference model. Specifically, our model parameterizes mean and variance for each time-stamp with flexible neural networks, resulting in a non-stationary model that can work without the assumption of constant noise as commonly made by existing Markov models. However, such a flexibility may cause the model fragile to anomalies. To achieve robust density estimation which can also benefit detection tasks, we propose a smoothness-inducing prior over possible estimations. The proposed prior works as a regularizer that places penalty at non-smooth reconstructions. Our model is learned efficiently with a novel stochastic gradient variational Bayes estimator. In particular, we study two decision criteria for anomaly detection: reconstruction probability and reconstruction error. We show the effectiveness of our model on both synthetic datasets and public real-world benchmarks.

cs.LG↗
arXiv2020

Reflection features in the X-ray spectrum of Fairall 9 and implications for tests of general relativity

X-ray reflection spectroscopy is potentially a powerful tool to probe the spacetime geometry around astrophysical black holes and test general relativity in the strong field regime. However, precision tests of general relativity are only possible if we employ the correct astrophysical model and we can limit the systematic uncertainties. It is thus crucial to select the sources and the observations most suitable for these tests. In this work, we analyze simultaneous observations of XMM-Newton and NuSTAR of the supermassive black hole in Fairall 9. This source has a number of properties that make it a promising candidate for tests of general relativity using X-ray reflection spectroscopy. Nevertheless, we find that with the available data there is not a unique interpretation of the spectrum of Fairall 9, which prevents, for the moment, to use this source for robust tests of general relativity. This issue may be solved by future X-ray missions with a higher energy resolution near the iron line.

gr-qc↗
arXiv2019

Explicit Shape Encoding for Real-Time Instance Segmentation

In this paper, we propose a novel top-down instance segmentation framework based on explicit shape encoding, named \textbf{ESE-Seg}. It largely reduces the computational consumption of the instance segmentation by explicitly decoding the multiple object shapes with tensor operations, thus performs the instance segmentation at almost the same speed as the object detection. ESE-Seg is based on a novel shape signature Inner-center Radius (IR), Chebyshev polynomial fitting and the strong modern object detectors. ESE-Seg with YOLOv3 outperforms the Mask R-CNN on Pascal VOC 2012 at mAP$^r$@0.5 while 7 times faster.

cs.CV↗
arXiv2019

Dense Adaptive Cascade Forest: A Self Adaptive Deep Ensemble for Classification Problems

Recent researches have shown that deep forest ensemble achieves a considerable increase in classification accuracy compared with the general ensemble learning methods, especially when the training set is small. In this paper, we take advantage of deep forest ensemble and introduce the Dense Adaptive Cascade Forest (daForest). Our model has a better performance than the original Cascade Forest with three major features: first, we apply SAMME.R boosting algorithm to improve the performance of the model. It guarantees the improvement as the number of layers increases. Second, our model connects each layer to the subsequent ones in a feed-forward fashion, which enhances the capability of the model to resist performance degeneration. Third, we add a hyper-parameters optimization layer before the first classification layer, making our model spend less time to set up and find the optimal hyper-parameters. Experimental results show that daForest performs significantly well, and in some cases, even outperforms neural networks and achieves state-of-the-art results.

cs.LG↗
arXiv2019

Visual Rhythm Prediction with Feature-Aligning Network

In this paper, we propose a data-driven visual rhythm prediction method, which overcomes the previous works' deficiency that predictions are made primarily by human-crafted hard rules. In our approach, we first extract features including original frames and their residuals, optical flow, scene change, and body pose. These visual features will be next taken into an end-to-end neural network as inputs. Here we observe that there are some slight misaligning between features over the timeline and assume that this is due to the distinctions between how different features are computed. To solve this problem, the extracted features are aligned by an elaborately designed layer, which can also be applied to other models suffering from mismatched features, and boost performance. Then these aligned features are fed into sequence labeling layers implemented with BiLSTM and CRF to predict the onsets. Due to the lack of existing public training and evaluation set, we experiment on a dataset constructed by ourselves based on professionally edited Music Videos (MVs), and the F1 score of our approach reaches 79.6.

cs.CV↗
arXiv2017

Forward Backward SDEs in Weak Formulation

Although having been developed for more than two decades, the theory of forward backward stochastic differential equations is still far from complete. In this paper, we take one step back and investigate the formulation of FBSDEs. Motivated from several considerations, both in theory and in applications, we propose to study FBSDEs in weak formulation, rather than the strong formulation in the standard literature. That is, the backward SDE is driven by the forward component, instead of by the Brownian motion noise. We establish the Feyman-Kac formula for FBSDEs in weak formulation, both in classical and in viscosity sense. Our new framework is efficient especially when the diffusion part of the forward equation involves the $Z$-component of the backward equation.

math.PR↗
arXiv2017

Chemical Complementarity between the Gas Phase of the Interstellar Medium and the Rocky Material of Our Planetary System

We compare the elemental depletions in the gas phase of the interstellar medium (ISM) with the elemental depletions in the rocky material of our Solar System. Our analysis finds a high degree of chemical complementarity: elements depleted in the gas phase of the ISM are enriched in the rocky material of our Solar System, and vice versa. This chemical complementarity reveals the generic connections between interstellar dust and rocky planetary material. We use an inheritance model to explain the formation of primordial grains in the solar nebula. The primary dust grains inherited from the ISM, in combination with the secondary ones condensed from the solar nebula, constitute the primordial rocky material of our planetary system, from which terrestrial planets are formed through the effects of the progressive accretion and sublimation. The semi-major-axis-dependence of the chemical composition of rocky planetary material is also observed by comparing elemental depletions in the Earth, CI chondrites and other types of carbonaceous chondrites.

astro-ph.EP↗
arXiv2017

OMNIRank: Risk Quantification for P2P Platforms with Deep Learning

P2P lending presents as an innovative and flexible alternative for conventional lending institutions like banks, where lenders and borrowers directly make transactions and benefit each other without complicated verifications. However, due to lack of specialized laws, delegated monitoring and effective managements, P2P platforms may spawn potential risks, such as withdraw failures, investigation involvements and even runaway bosses, which cause great losses to lenders and are especially serious and notorious in China. Although there are abundant public information and data available on the Internet related to P2P platforms, challenges of multi-sourcing and heterogeneity matter. In this paper, we promote a novel deep learning model, OMNIRank, which comprehends multi-dimensional features of P2P platforms for risk quantification and produces scores for ranking. We first construct a large-scale flexible crawling framework and obtain great amounts of multi-source heterogeneous data of domestic P2P platforms since 2007 from the Internet. Purifications like duplication and noise removal, null handing, format unification and fusion are applied to improve data qualities. Then we extract deep features of P2P platforms via text comprehension, topic modeling, knowledge graph and sentiment analysis, which are delivered as inputs to OMNIRank, a deep learning model for risk quantification of P2P platforms. Finally, according to rankings generated by OMNIRank, we conduct flourish data visualizations and interactions, providing lenders with comprehensive information supports, decision suggestions and safety guarantees.

cs.CY↗
arXiv2016

Towards Hybrid Cloud-assisted Crowdsourced Live Streaming: Measurement and Analysis

Crowdsourced Live Streaming (CLS), most notably Twitch.tv, has seen explosive growth in its popularity in the past few years. In such systems, any user can lively broadcast video content of interest to others, e.g., from a game player to many online viewers. To fulfill the demands from both massive and heterogeneous broadcasters and viewers, expensive server clusters have been deployed to provide video ingesting and transcoding services. Despite the existence of highly popular channels, a significant portion of the channels is indeed unpopular. Yet as our measurement shows, these broadcasters are consuming considerable system resources; in particular, 25% (resp. 30%) of bandwidth (resp. computation) resources are used by the broadcasters who do not have any viewers at all. In this paper, we closely examine the challenge of handling unpopular live-broadcasting channels in CLS systems and present a comprehensive solution for service partitioning on hybrid cloud. The trace-driven evaluation shows that our hybrid cloud-assisted design can smartly assign ingesting and transcoding tasks to the elastic cloud virtual machines, providing flexible system deployment cost-effectively.

cs.MM↗
arXiv2016

Exploring triad-rich substructures by graph-theoretic characterizations in complex networks

One of the most important problems in complex networks is how to detect metadata groups accurately. The main challenge lies in the fact that traditional structural communities do not always capture the intrinsic features of metadata groups. Motivated by the observation that metadata groups in PPI networks tend to consist of an abundance of interacting triad motifs, we define a 2-club substructure with diameter 2 which possessing triad-rich property to describe a metadata group. Based on the triad-rich substructure, we design a DIVision Algorithm using our proposed edge Niche Centrality DIVANC to detect metadata groups effectively in complex networks. We also extend DIVANC to detect overlapping metadata groups by proposing a simple 2-hop overlapping strategy. To verify the effectiveness of triad-rich substructures, we compare DIVANC with existing algorithms on PPI networks, LFR synthetic networks and football networks. The experimental results show that DIVANC outperforms most other algorithms significantly and, in particular, can detect sparse metadata groups.

physics.soc-ph↗
arXiv2014

High-performance controllable ambipolar infrared phototransistors based on graphene-quantum dot hybrid

The field effect transistors (FETs) exhibited ultrahigh responsivity (107 A/W) to infrared light with great improvement of mobility in graphene / PbS quantum dot (QD) hybrid. These reported transistors are either unipolar or depletion mode devices. In this paper, we presented and fabricated conveniently-controlled grapheme / PbS QD hybrid FETs. Through the investigation on electric and optoelectronic properties, the ambipolar FETs (normally OFF) can be switched ON by raising gate voltage (VG) up to 3.7 V and -0.8 V in the first and third quadrants. Near these thresholds (VT) each carrier species shows comparable mobility (~ 300 cm2V-1s-1). Photo-responsivity reach ~ 107 A/W near each threshold and it will linearly increases with (VG-VT). These hybrid FETs become strongly competitive candidates for devices in flexible integrated circuits with low cost, large area, low-energy consumption and high performances.

physics.ins-det↗