Searcharxiv⌕ Search

arXiv subjects

Min Zhou

Publications and source records attributed to Min Zhou.

86 records · Page 5Linked to original sources
arXiv2021

Scaling Up Graph Neural Networks Via Graph Coarsening

Scalability of graph neural networks remains one of the major challenges in graph machine learning. Since the representation of a node is computed by recursively aggregating and transforming representation vectors of its neighboring nodes from previous layers, the receptive fields grow exponentially, which makes standard stochastic optimization techniques ineffective. Various approaches have been proposed to alleviate this issue, e.g., sampling-based methods and techniques based on pre-computation of graph filters. In this paper, we take a different approach and propose to use graph coarsening for scalable training of GNNs, which is generic, extremely simple and has sublinear memory and time costs during training. We present extensive theoretical analysis on the effect of using coarsening operations and provides useful guidance on the choice of coarsening methods. Interestingly, our theoretical analysis shows that coarsening can also be considered as a type of regularization and may improve the generalization. Finally, empirical results on real world datasets show that, simply applying off-the-shelf coarsening methods, we can reduce the number of nodes by up to a factor of ten without causing a noticeable downgrade in classification accuracy.

cs.LG↗
arXiv2021

An Influence-based Approach for Root Cause Alarm Discovery in Telecom Networks

Alarm root cause analysis is a significant component in the day-to-day telecommunication network maintenance, and it is critical for efficient and accurate fault localization and failure recovery. In practice, accurate and self-adjustable alarm root cause analysis is a great challenge due to network complexity and vast amounts of alarms. A popular approach for failure root cause identification is to construct a graph with approximate edges, commonly based on either event co-occurrences or conditional independence tests. However, considerable expert knowledge is typically required for edge pruning. We propose a novel data-driven framework for root cause alarm localization, combining both causal inference and network embedding techniques. In this framework, we design a hybrid causal graph learning method (HPCI), which combines Hawkes Process with Conditional Independence tests, as well as propose a novel Causal Propagation-Based Embedding algorithm (CPBE) to infer edge weights. We subsequently discover root cause alarms in a real-time data stream by applying an influence maximization algorithm on the weighted graph. We evaluate our method on artificial data and real-world telecom data, showing a significant improvement over the best baselines.

cs.LG↗
arXiv2021

Multi-objective Herglotz' variational principle and cooperative Hamilton-Jacobi systems

We study a multi-objective variational problem of Herglotz' type with cooperative linear coupling. We established the associated Euler-Lagrange equations and the characteristic system for cooperative weakly coupled systems of Hamilton-Jacobi equations. We also established the relation of the value functions of this variational problem with the viscosity solutions of cooperative weakly coupled systems of Hamilton-Jacobi equations. Comparing to the previous work in stochastic frame, this approach affords a pure deterministic explanation of this problem under more general conditions. We also showed this approach is valid for general linearly coupling matrix for short time.

math.AP↗
arXiv2021

Visible and Near-infrared Microdisk Resonators on a 4H-Silicon-Carbide-on-Insulator Platform

Wavelength-sized microdisk resonators were fabricated on a single crystalline 4H-silicon-carbide-oninsulator platform (4H-SiCOI). By carrying out microphotoluminescence measurements at room temperature, we show that the microdisk resonators support whispering-gallery modes (WGMs) with quality factors up to $5.25 \times 10^3$ and mode volumes down to $2.69 \times(λ/n)^3$ at the visible and near-infrared wavelengths. Moreover, the demonstrated wavelength-sized microdisk resonators exhibit WGMs whose resonant wavelengths compatible with the zero-phonon lines of spin defects in 4H-SiCOI, making them a promising candidate for applications in cavity quantum electrodynamics and integrated quantum photonic circuits.

physics.optics↗
arXiv2020

BOLT-SSI: A Statistical Approach to Screening Interaction Effects for Ultra-High Dimensional Data

Detecting interaction effects among predictors on the response variable is a crucial step in various applications. In this paper, we first propose a simple method for sure screening interactions (SSI). Although its computation complexity is $O(p^2n)$, SSI works well for problems of moderate dimensionality (e.g., $p=10^3\sim10^4$), without the heredity assumption. To ultra-high dimensional problems (e.g., $p = 10^6$), motivated by discretization associated Boolean representation and operations and the contingency table for discrete variables, we propose a fast algorithm, named "BOLT-SSI". The statistical theory has been established for SSI and BOLT-SSI, guaranteeing their sure screening property. The performance of SSI and BOLT-SSI are evaluated by comprehensive simulation and real case studies. Numerical results demonstrate that SSI and BOLT-SSI can often outperform their competitors in terms of computational efficiency and statistical accuracy. The proposed method can be applied for fully detecting interactions with more than 300,000 predictors. Based on this study, we believe that there is a great need to rethink the relationship between statistical accuracy and computational efficiency. We have shown that the computational performance of a statistical method can often be greatly improved by exploring the advantages of computational architecture with a tolerable loss of statistical accuracy.

stat.ME↗
arXiv2020

Spatio-Temporal Hybrid Graph Convolutional Network for Traffic Forecasting in Telecommunication Networks

Telecommunication networks play a critical role in modern society. With the arrival of 5G networks, these systems are becoming even more diversified, integrated, and intelligent. Traffic forecasting is one of the key components in such a system, however, it is particularly challenging due to the complex spatial-temporal dependency. In this work, we consider this problem from the aspect of a cellular network and the interactions among its base stations. We thoroughly investigate the characteristics of cellular network traffic and shed light on the dependency complexities based on data collected from a densely populated metropolis area. Specifically, we observe that the traffic shows both dynamic and static spatial dependencies as well as diverse cyclic temporal patterns. To address these complexities, we propose an effective deep-learning-based approach, namely, Spatio-Temporal Hybrid Graph Convolutional Network (STHGCN). It employs GRUs to model the temporal dependency, while capturing the complex spatial dependency through a hybrid-GCN from three perspectives: spatial proximity, functional similarity, and recent trend similarity. We conduct extensive experiments on real-world traffic datasets collected from telecommunication networks. Our experimental results demonstrate the superiority of the proposed model in that it consistently outperforms both classical methods and state-of-the-art deep learning models, while being more robust and stable.

cs.LG↗
arXiv2019

Progressive Feature Polishing Network for Salient Object Detection

Feature matters for salient object detection. Existing methods mainly focus on designing a sophisticated structure to incorporate multi-level features and filter out cluttered features. We present Progressive Feature Polishing Network (PFPN), a simple yet effective framework to progressively polish the multi-level features to be more accurate and representative. By employing multiple Feature Polishing Modules (FPMs) in a recurrent manner, our approach is able to detect salient objects with fine details without any post-processing. A FPM parallelly updates the features of each level by directly incorporating all higher level context information. Moreover, it can keep the dimensions and hierarchical structures of the feature maps, which makes it flexible to be integrated with any CNN-based models. Empirical experiments show that our results are monotonically getting better with increasing number of FPMs. Without bells and whistles, PFPN outperforms the state-of-the-art methods significantly on five benchmark datasets under various evaluation metrics.

cs.CV↗
arXiv2018

Scattering Statistics in Nonlinear Wave Chaotic Systems

The Random Coupling Model (RCM) is a statistical approach for studying the scattering properties of linear wave chaotic systems in the semi-classical regime. Its success has been experimentally verified in various over-moded wave settings, including both microwave and acoustic systems. It is of great interest to extend its use to nonlinear systems. This paper studies the impact of a nonlinear port on the measured statistical electromagnetic properties of a ray-chaotic complex enclosure in the short wavelength limit. A Vector Network Analyzer is upgraded with a high power option which enables calibrated scattering (S) parameter measurements up to +43 dBm. By attaching a diode to the excitation antenna, amplitude-dependent S-parameters are observed. We have systematically studied how the key components in the RCM are affected by this nonlinear port, including the radiation impedance, short ray orbit corrections, and statistical properties. By applying the newly developed radiation efficiency extension to the RCM, we find that the diode admittance increases with excitation amplitude. This reduces the amount of power entering the cavity through the port, so that the diode effectively acts as a protection element.

physics.class-ph↗
arXiv2018

Short-term load forecasting using optimized LSTM networks based on EMD

Short-term load forecasting is one of the crucial sections in smart grid. Precise forecasting enables system operators to make reliable unit commitment and power dispatching decisions. With the advent of big data, a number of artificial intelligence techniques such as back propagation, support vector machine have been used to predict the load of the next day. Nevertheless, due to the noise of raw data and the randomness of power load, forecasting errors of existing approaches are relatively large. In this study, a short-term load forecasting method is proposed on the basis of empirical mode decomposition and long short-term memory networks, the parameters of which are optimized by a particle swarm optimization algorithm. Essentially, empirical mode decomposition can decompose the original time series of historical data into relatively stationary components and long short-term memory network is able to emphasize as well as model the timing of data, the joint use of which is expected to effectively apply the characteristics of data itself, so as to improve the predictive accuracy. The effectiveness of this research is exemplified on a realistic data set, the experimental results of which show that the proposed method has higher forecasting accuracy and applicability, as compared with existing methods.

eess.SP↗
arXiv2018

Study of the elastocaloric effect and mechanical behavior for the NiTi shape memory alloys

The NiTi shape memory alloy exhibited excellent superelastic property and elastocaloric effect. Large temperature changes of 30 K upon loading and -19 K upon unloading were obtained at room temperature, which were higher than those of the other NiTi-based materials and among the highest values reported in the elastocaloric materials. The asymmetry of the measured temperature changes between loading and unloading process was ascribed to the friction dissipation. The large temperature changes originated from the large entropy change during the stress-induced martensite transformation (MT) and the reverse MT. A large coefficient-of-performance of the material (COPmater) of 11.7 was obtained, which decreased with increasing the applied strain. These results are very attractive in the present solid-state cooling which is potential to replace the vapor compression refrigeration technologies.

cond-mat.mtrl-sci↗
arXiv2017

Nonlinear Wave Chaos: Statistics of Second Harmonic Fields

Concepts from the field of wave chaos have been shown to successfully predict the statistical properties of linear electromagnetic fields in electrically large enclosures. The Random Coupling Model (RCM) describes these properties by incorporating both universal features described by Random Matrix Theory and the system-specific features of particular system realizations. In an effort to extend this approach to the nonlinear domain, we add an active nonlinear frequency-doubling circuit to an otherwise linear wave chaotic system, and we measure the statistical properties of the resulting second harmonic fields. We develop an RCM-based model of this system as two linear chaotic cavities coupled by means of a nonlinear transfer function. The harmonic field strengths are predicted to be the product of two statistical quantities and the nonlinearity characteristics. Statistical results from measurement-based calculation, RCM-based simulation, and direct experimental measurements are compared and show good agreement over many decades of power.

nlin.CD↗
arXiv2016

Testing consistency of general relativity with kinematic and dynamical probes

In this work, we test consistency relations between a kinematic probe, the observational Hubble data, and a dynamical probe, the growth rates for cosmic large scale structure, which should hold if general relativity is the correct theory of gravity on cosmological scales. Moreover, we summarize the development history of parametrization in testings and make an improvement of it. Taking advantage of the Hubble parameter given from both parametric and non-parametric methods, we propose three equations and test two of them performed by means of two-dimensional parameterizations, including one using trigonometric functions we propose. As a result, it is found that the consistency relations satisfies well at $1σ$ CL and trigonometric functions turn out to be efficient tools in parameterizations. Furthermore, in order to confirm the validity of our test, we introduce a model of modified gravity, DGP model and compare the testing results in the cases of $Λ$CDM, "DGP in GR" and DGP model with mock data. It can be seen that it is the establishing of consistency relations which dominates the results of the testing. Overall, the present observational Hubble data and growth rate data favor convincingly that the general relativity is the correct theory of gravity on cosmological scales.

astro-ph.CO↗