arXiv subjects

Liang Zhao

Publications and source records attributed to Liang Zhao.

At least 433 records · Page 24Linked to original sources

arXiv2019

DynGraph2Seq: Dynamic-Graph-to-Sequence Interpretable Learning for Health Stage Prediction in Online Health Forums

Online health communities such as the online breast cancer forum enable patients (i.e., users) to interact and help each other within various subforums, which are subsections of the main forum devoted to specific health topics. The changing nature of the users' activities in different subforums can be strong indicators of their health status changes. This additional information could allow health-care organizations to respond promptly and provide additional help for the patient. However, modeling complex transitions of an individual user's activities among different subforums over time and learning how these correspond to his/her health stage are extremely challenging. In this paper, we first formulate the transition of user activities as a dynamic graph with multi-attributed nodes, then formalize the health stage inference task as a dynamic graph-to-sequence learning problem, and hence propose a novel dynamic graph-to-sequence neural networks architecture (DynGraph2Seq) to address all the challenges. Our proposed DynGraph2Seq model consists of a novel dynamic graph encoder and an interpretable sequence decoder that learn the mapping between a sequence of time-evolving user activity graphs and a sequence of target health stages. We go on to propose dynamic graph hierarchical attention mechanisms to facilitate the necessary multi-level interpretability. A comprehensive experimental analysis of its use for a health stage prediction task demonstrates both the effectiveness and the interpretability of the proposed models.

cs.LG↗

arXiv2019

Counting Roots of a Polynomial in a Convex Compact Region by Means of Winding Number Calculation via Sampling

In this paper we propose a novel efficient algorithm for calculating winding numbers, aiming at counting the number of roots of a given polynomial in a convex region on the complex plane. This algorithm can be used for counting and exclusion tests in a subdivision algorithms for polynomial root-finding, and would be especially usefull in application scenarios where high-precision polynomial coefficients are hard to obtain but we succeed with counting already by using polynomial evaluation with lower precision. We provide the pseudo code of the algorithm, proof of its correctness as well as estimation of its complexity.

math.NA↗

arXiv2019

Existence and convergence of solutions for nonlinear biharmonic equations on graphs

In this paper, we first prove some propositions of Sobolev spaces defined on a locally finite graph $G=(V,E)$, which are fundamental when dealing with equations on graphs under the variational framework. Then we consider a nonlinear biharmonic equation $$ Δ^{2} u -Δu+(λa+1)u= |u|^{p-2}u $$ on $G=(V,E)$. Under some suitable assumptions, we prove that for any $λ>1$ and $p>2$, the equation admits a ground state solution $u_λ$. Moreover, we prove that as $λ\rightarrow +\infty$, the solutions $u_λ$ converge to a solution of the equation \begin{align*} \begin{cases} Δ^{2}u -Δu+u = |u|^{p-2}u, &\text{in}\ \ Ω, u=0, &\text{on}\ \ \partialΩ, \end{cases} \end{align*} where $Ω=\{x\in V: a(x)=0\}$ is the potential well and $\partialΩ$ denotes the the boundary of $Ω$.

math.AP↗

arXiv2019

Pyramid: Machine Learning Framework to Estimate the Optimal Timing and Resource Usage of a High-Level Synthesis Design

The emergence of High-Level Synthesis (HLS) tools shifted the paradigm of hardware design by making the process of mapping high-level programming languages to hardware design such as C to VHDL/Verilog feasible. HLS tools offer a plethora of techniques to optimize designs for both area and performance, but resource usage and timing reports of HLS tools mostly deviate from the post-implementation results. In addition, to evaluate a hardware design performance, it is critical to determine the maximum achievable clock frequency. Obtaining such information using static timing analysis provided by CAD tools is difficult, due to the multitude of tool options. Moreover, a binary search to find the maximum frequency is tedious, time-consuming, and often does not obtain the optimal result. To address these challenges, we propose a framework, called Pyramid, that uses machine learning to accurately estimate the optimal performance and resource utilization of an HLS design. For this purpose, we first create a database of C-to-FPGA results from a diverse set of benchmarks. To find the achievable maximum clock frequency, we use Minerva, which is an automated hardware optimization tool. Minerva determines the close-to-optimal settings of tools, using static timing analysis and a heuristic algorithm, and targets either optimal throughput or throughput-to-area. Pyramid uses the database to train an ensemble machine learning model to map the HLS-reported features to the results of Minerva. To this end, Pyramid re-calibrates the results of HLS to bridge the accuracy gap and enable developers to estimate the throughput or throughput-to-area of hardware design with more than 95% accuracy and alleviates the need to perform actual implementation for estimation.

cs.AR↗

arXiv2019

An observable time series based SLAM algorithm for deforming environment

In this paper, we study the back-end of simultaneous localization and mapping (SLAM) problem in deforming environment, where robot localizes itself and tracks multiple non-rigid soft surface using its onboard sensor measurements. An elaborate analysis is conducted on conventional deformation modelling method, Embedded Deformation (ED) graph. We demonstrate and prove that the ED graph widely used in such scenarios is unobservable and leads to multiple solutions unless suitable priors are provided. Example as well as theoretical prove are provided to show the ambiguity of ED graph and camera pose. In modelling non-rigid scenario with ED graph, motion priors of the deforming environment is essential to separate robot pose and deforming environment. The conclusion can be extrapolated to any free form deformation formulation. In solving the observability, this research proposes a preliminary deformable SLAM approach to estimate robot pose in complex environments that exhibits regular motion. A strategy that approximates deformed shape using a linear combination of several previous shapes is proposed to avoid the ambiguity in robot movement and rigid and non-rigid motions of the environment. Fisher information matrix rank analysis with a base case is discussed to prove the effectiveness. Moreover, the proposed algorithm is validated extensively on Monte Carlo simulations and real experiments. It is demonstrated that the new algorithm significantly outperforms conventional rigid SLAM and ED based SLAM especially in scenarios where there is large deformation.

cs.RO↗

arXiv2019

Non-Bayesian Social Learning with Imperfect Private Signal Structure

As one of the classic models that describe the belief dynamics over social networks, a non-Bayesian social learning model assumes that members in the network possess accurate signal knowledge through the process of Bayesian inference. In order to make the non-Bayesian social learning model more applicable to human and animal societies, this paper extended this model by assuming the existence of private signal structure bias. Each social member in each time step uses an imperfect signal knowledge to form its Bayesian part belief and then incorporates its neighbors' beliefs into this Bayesian part belief to form a new belief report. First, we investigated the intrinsic learning ability of an isolated agent and deduced the conditions that the signal structure needs to satisfy for this isolated agent to make an eventually correct decision. According to these conditions, agents' signal structures were further divided into three different types, "conservative," "radical," and "negative." Then, we switched the context from isolated agents to a connected network; our propositions and simulations show that the conservative agents are the dominant force for the social network to learn the real state, while the other two types might prevent the network from successful learning. Although fragilities do exist in non-Bayesian social learning mechanism, "be more conservative" and "avoid overconfidence" could be effective strategies for each agent in the real social networks to collectively improve social learning processes and results.

cs.SI↗

arXiv2019

Interpreting and Evaluating Neural Network Robustness

Recently, adversarial deception becomes one of the most considerable threats to deep neural networks. However, compared to extensive research in new designs of various adversarial attacks and defenses, the neural networks' intrinsic robustness property is still lack of thorough investigation. This work aims to qualitatively interpret the adversarial attack and defense mechanism through loss visualization, and establish a quantitative metric to evaluate the neural network model's intrinsic robustness. The proposed robustness metric identifies the upper bound of a model's prediction divergence in the given domain and thus indicates whether the model can maintain a stable prediction. With extensive experiments, our metric demonstrates several advantages over conventional adversarial testing accuracy based robustness estimation: (1) it provides a uniformed evaluation to models with different structures and parameter scales; (2) it over-performs conventional accuracy based robustness estimation and provides a more reliable evaluation that is invariant to different test settings; (3) it can be fast generated without considerable testing cost.

cs.LG↗

arXiv2019

Dynamic jamming of dense suspensions under tilted impact

Dense particulate suspensions can not only increase their viscosity and shear thicken under external forcing, but also jam into a solid-like state that is fully reversible when the force is removed. An impact on the surface of a dense suspension can trigger this jamming process by generating a shear front that propagates into the bulk of the system. Tracking and visualizing such a front is difficult because suspensions are optically opaque and the front can propagate as fast as several meters per second. Recently, high-speed ultrasound imaging has been used to overcome this problem and extract two-dimensional sections of the flow field associated with jamming front propagation. Here we extend this method to reconstruct the three-dimensional flow field. This enables us to investigate the evolution of jamming fronts for which axisymmetry cannot be assumed, such as impact at angles tilted away from the normal to the free surface of the suspension. We find that sufficiently far from solid boundaries the resulting flow field is approximately identical to that generated by normal impact, but rotated and aligned with the angle of impact. However, once the front approaches the solid boundary at the bottom of the container, it generates a squeeze flow that deforms the front profile and causes jamming to proceed in a non-axisymmetric manner.

cond-mat.soft↗

arXiv2019

Learning Good Representation via Continuous Attention

In this paper we present our scientific discovery that good representation can be learned via continuous attention during the interaction between Unsupervised Learning(UL) and Reinforcement Learning(RL) modules driven by intrinsic motivation. Specifically, we designed intrinsic rewards generated from UL modules for driving the RL agent to focus on objects for a period of time and to learn good representations of objects for later object recognition task. We evaluate our proposed algorithm in both with and without extrinsic reward settings. Experiments with end-to-end training in simulated environments with applications to few-shot object recognition demonstrated the effectiveness of the proposed algorithm.

cs.LG↗

arXiv2019

Algorithms to compute the Burrows-Wheeler Similarity Distribution

The Burrows-Wheeler transform (BWT) is a well studied text transformation widely used in data compression and text indexing. The BWT of two strings can also provide similarity measures between them, based on the observation that the more their symbols are intermixed in the transformation, the more the strings are similar. In this article we present two new algorithms to compute similarity measures based on the BWT for string collections. In particular, we present practical and theoretical improvements to the computation of the Burrows-Wheeler similarity distribution for all pairs of strings in a collection. Our algorithms take advantage of the BWT computed for the concatenation of all strings, and use compressed data structures that allow reducing the running time with a small memory footprint, as shown by a set of experiments with real and artificial datasets.

cs.DS↗

arXiv2019

CircConv: A Structured Convolution with Low Complexity

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation resource and weight storage, thereby limiting the practical deployment of DNNs. To overcome these limitations, this paper proposes to impose the circulant structure to the construction of convolutional layers, and hence leads to circulant convolutional layers (CircConvs) and circulant CNNs. The circulant structure and models can be either trained from scratch or re-trained from a pre-trained non-circulant model, thereby making it very flexible for different training environments. Through extensive experiments, such strong structure-imposing approach is proved to be able to substantially reduce the number of parameters of convolutional layers and enable significant saving of computational cost by using fast multiplication of the circulant tensor.

cs.CV↗

arXiv2019

Robust Regression via Online Feature Selection under Adversarial Data Corruption

The presence of data corruption in user-generated streaming data, such as social media, motivates a new fundamental problem that learns reliable regression coefficient when features are not accessible entirely at one time. Until now, several important challenges still cannot be handled concurrently: 1) corrupted data estimation when only partial features are accessible; 2) online feature selection when data contains adversarial corruption; and 3) scaling to a massive dataset. This paper proposes a novel RObust regression algorithm via Online Feature Selection (\textit{RoOFS}) that concurrently addresses all the above challenges. Specifically, the algorithm iteratively updates the regression coefficients and the uncorrupted set via a robust online feature substitution method. We also prove that our algorithm has a restricted error bound compared to the optimal solution. Extensive empirical experiments in both synthetic and real-world datasets demonstrated that the effectiveness of our new method is superior to that of existing methods in the recovery of both feature selection and regression coefficients, with very competitive efficiency.

cs.LG↗

arXiv2019

WALL-E: An Efficient Reinforcement Learning Research Framework

There are two halves to RL systems: experience collection time and policy learning time. For a large number of samples in rollouts, experience collection time is the major bottleneck. Thus, it is necessary to speed up the rollout generation time with multi-process architecture support. Our work, dubbed WALL-E, utilizes multiple rollout samplers running in parallel to rapidly generate experience. Due to our parallel samplers, we experience not only faster convergence times, but also higher average reward thresholds. For example, on the MuJoCo HalfCheetah-v2 task, with $N = 10$ parallel sampler processes, we are able to achieve much higher average return than those from using only a single process architecture.

cs.LG↗

arXiv2019

Global existence of the harmonic map heat flow into Lorentzian manifolds

We investigate a parabolic-elliptic system for maps $(u,v)$ from a compact Riemann surface $M$ into a Lorentzian manifold $N\times{\mathbb{R}}$ with a warped product metric. That system turns the harmonic map type equations into a parabolic system, but keeps the $v$-equation as a nonlinear second order constraint along the flow. We prove a global existence result of the parabolic-elliptic system by assuming either some geometric conditions on the target Lorentzian manifold or small energy of the initial maps. The result implies the existence of a Lorentzian harmonic map in a given homotopy class with fixed boundary data.

math.DG↗

arXiv2018

From spatio-temporal data to chronological networks: An application to wildfire analysis

Network theory has established itself as an appropriate tool for complex systems analysis and pattern recognition. In the context of spatiotemporal data analysis, correlation networks are used in the vast majority of works. However, the Pearson correlation coefficient captures only linear relationships and does not correctly capture recurrent events. This missed information is essential for temporal pattern recognition. In this work, we propose a chronological network construction process that is capable of capturing various events. Similar to the previous methods, we divide the area of study into grid cells and represent them by nodes. In our approach, links are established if two consecutive events occur in two different nodes. Our method is computationally efficient, adaptable to different time windows and can be applied to any spatiotemporal data set. As a proof-of-concept, we evaluated the proposed approach by constructing chronological networks from the MODIS dataset for fire events in the Amazon basin. We explore two data analytic approaches: one static and another temporal. The results show some activity patterns on the fire events and a displacement phenomenon over the year. The validity of the analyses in this application indicates that our data modeling approach is very promising for spatio-temporal data mining.

physics.soc-ph↗

arXiv2018

Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a survey

Topic modeling is one of the most powerful techniques in text mining for data mining, latent data discovery, and finding relationships among data, text documents. Researchers have published many articles in the field of topic modeling and applied in various fields such as software engineering, political science, medical and linguistic science, etc. There are various methods for topic modeling, which Latent Dirichlet allocation (LDA) is one of the most popular methods in this field. Researchers have proposed various models based on the LDA in topic modeling. According to previous work, this paper can be very useful and valuable for introducing LDA approaches in topic modeling. In this paper, we investigated scholarly articles highly (between 2003 to 2016) related to Topic Modeling based on LDA to discover the research development, current trends and intellectual structure of topic modeling. Also, we summarize challenges and introduce famous tools and datasets in topic modeling based on LDA.

cs.IR↗

arXiv2018

A New Hybrid Consensus Protocol: Deterministic Proof Of Work

The Decentralized-Consistent-Scale (DCS) Triangle defines three dimensions that illustrate the tradeoffs of the blockchain consensus mechanism. In this paper, we propose a new hybrid consensus protocol, called Deterministic Proof of Work (DPoW), which can reach high levels of scalability and consistency without significant reduction to decentralization. Our protocol introduces a Map-reduce PoW mining algorithm to perform alongside Practical Byzantine Fault Tolerance (PBFT) verification, which together allow for transactions to be confirmed immediately, largely improving scalability. In addition, the protocol is designed such that forking cannot occur, ensuring strong consistency and security against a multitude of attacks. The Map-reduce PoW mining process ensures that no single entity can control the network, guaranteeing decentralization. We analyzed the security of our protocol by evaluating the possibility of double spending attacks, and furthermore, conducted experiments which demonstrate our claims.

cs.CR↗

arXiv2018

Toward Creating Subsurface Camera

In this article, the framework and architecture of Subsurface Camera (SAMERA) is envisioned and described for the first time. A SAMERA is a geophysical sensor network that senses and processes geophysical sensor signals, and computes a 3D subsurface image in-situ in real-time. The basic mechanism is: geophysical waves propagating/reflected/refracted through subsurface enter a network of geophysical sensors, where a 2D or 3D image is computed and recorded; a control software may be connected to this network to allow view of the 2D/3D image and adjustment of settings such as resolution, filter, regularization and other algorithm parameters. System prototypes based on seismic imaging have been designed. SAMERA technology is envisioned as a game changer to transform many subsurface survey and monitoring applications, including oil/gas exploration and production, subsurface infrastructures and homeland security, wastewater and CO2 sequestration, earthquake and volcano hazard monitoring. The system prototypes for seismic imaging have been built. Creating SAMERA requires an interdisciplinary collaboration and transformation of sensor networks, signal processing, distributed computing, and geophysical imaging.

eess.SP↗