arXiv subjects

Yang Li

Publications and source records attributed to Yang Li.

At least 1,189 records · Page 66Linked to original sources

arXiv2021

Optimal integrating learning for split questionnaire design type data

In the era of data science, it is common to encounter data with different subsets of variables obtained for different cases. An example is the split questionnaire design (SQD), which is adopted to reduce respondent fatigue and improve response rates by assigning different subsets of the questionnaire to different sampled respondents. A general question then is how to estimate the regression function based on such block-wise observed data. Currently, this is often carried out with the aid of missing data methods, which may unfortunately suffer intensive computational cost, high variability, and possible large modeling biases in real applications. In this article, we develop a novel approach for estimating the regression function for SQD-type data. We first construct a list of candidate models using available data-blocks separately, and then combine the estimates properly to make an efficient use of all the information. We show the resulting averaged model is asymptotically optimal in the sense that the squared loss and risk are asymptotically equivalent to those of the best but infeasible averaged estimator. Both simulated examples and an application to the SQD dataset from the European Social Survey show the promise of the proposed method.

stat.ME↗

arXiv2021

MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements

Hyperparameter optimization (HPO) is a fundamental problem in automatic machine learning (AutoML). However, due to the expensive evaluation cost of models (e.g., training deep learning models or training models on large datasets), vanilla Bayesian optimization (BO) is typically computationally infeasible. To alleviate this issue, Hyperband (HB) utilizes the early stopping mechanism to speed up configuration evaluations by terminating those badly-performing configurations in advance. This leads to two kinds of quality measurements: (1) many low-fidelity measurements for configurations that get early-stopped, and (2) few high-fidelity measurements for configurations that are evaluated without being early stopped. The state-of-the-art HB-style method, BOHB, aims to combine the benefits of both BO and HB. Instead of sampling configurations randomly in HB, BOHB samples configurations based on a BO surrogate model, which is constructed with the high-fidelity measurements only. However, the scarcity of high-fidelity measurements greatly hampers the efficiency of BO to guide the configuration search. In this paper, we present MFES-HB, an efficient Hyperband method that is capable of utilizing both the high-fidelity and low-fidelity measurements to accelerate the convergence of HPO tasks. Designing MFES-HB is not trivial as the low-fidelity measurements can be biased yet informative to guide the configuration search. Thus we propose to build a Multi- Fidelity Ensemble Surrogate (MFES) based on the generalized Product of Experts framework, which can integrate useful information from multi-fidelity measurements effectively. The empirical studies on the real-world AutoML tasks demonstrate that MFES-HB can achieve 3.3-8.9x speedups over the state-of-the-art approach - BOHB.

cs.LG↗

arXiv2021

Frequency support Scheme based on parametrized power curve for de-loaded Wind Turbine under various wind speed

With increased wind power penetration in modern power systems, wind plants are required to provide frequency support similar to conventional plants. However, for the existing frequency regulation scheme of wind turbines, the control gains in the auxiliary frequency controller are difficult to set because of the compromise of the frequency regulation performance and the stable operation of wind turbines, especially when the wind speed remains variable. This paper proposes a novel frequency regulation scheme (FRS) for de-loaded wind turbines. Instead of an auxiliary frequency controller, frequency support is provided by modifying the parametrized power versus rotor speed curve, including the inertia power versus rotor speed curve and the droop power versus rotor speed curve. The advantage of the proposed scheme is that it does not contain any control gains and generally adapts to different wind speeds. Further, the proposed scheme can work for the whole section of wind speed without wind speed measurement information. The compared simulation results demonstrate the scheme improves the system frequency response while ensuring the stable operation of doubly-fed induction generators (DFIGs)-based variable-speed wind turbines (VSWTs) under various wind conditions. Furthermore, the scheme prevents rotor speed overdeceleration even when the wind speed decreases during frequency regulation control.

eess.SP↗

arXiv2021

Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization

Data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets. However, recent deep learning models have moved forward from independent and identically distributed data to graph-structured data, such as social networks, e-commerce user-item graphs, and knowledge graphs. This evolution has led to the emergence of Graph Neural Networks (GNNs) that go beyond the models existing data selection methods are designed for. Therefore, we present Grain, an efficient framework that opens up a new perspective through connecting data selection in GNNs with social influence maximization. By exploiting the common patterns of GNNs, Grain introduces a novel feature propagation concept, a diversified influence maximization objective with novel influence and diversity functions, and a greedy algorithm with an approximation guarantee into a unified framework. Empirical studies on public datasets demonstrate that Grain significantly improves both the performance and efficiency of data selection (including active learning and core-set selection) for GNNs. To the best of our knowledge, this is the first attempt to bridge two largely parallel threads of research, data selection, and social influence maximization, in the setting of GNNs, paving new ways for improving data efficiency.

cs.LG↗

arXiv2021

ROD: Reception-aware Online Distillation for Sparse Graphs

Graph neural networks (GNNs) have been widely used in many graph-based tasks such as node classification, link prediction, and node clustering. However, GNNs gain their performance benefits mainly from performing the feature propagation and smoothing across the edges of the graph, thus requiring sufficient connectivity and label information for effective propagation. Unfortunately, many real-world networks are sparse in terms of both edges and labels, leading to sub-optimal performance of GNNs. Recent interest in this sparse problem has focused on the self-training approach, which expands supervised signals with pseudo labels. Nevertheless, the self-training approach inherently cannot realize the full potential of refining the learning performance on sparse graphs due to the unsatisfactory quality and quantity of pseudo labels. In this paper, we propose ROD, a novel reception-aware online knowledge distillation approach for sparse graph learning. We design three supervision signals for ROD: multi-scale reception-aware graph knowledge, task-based supervision, and rich distilled knowledge, allowing online knowledge transfer in a peer-teaching manner. To extract knowledge concealed in the multi-scale reception fields, ROD explicitly requires individual student models to preserve different levels of locality information. For a given task, each student would predict based on its reception-scale knowledge, while simultaneously a strong teacher is established on-the-fly by combining multi-scale knowledge. Our approach has been extensively evaluated on 9 datasets and a variety of graph-based tasks, including node classification, link prediction, and node clustering. The result demonstrates that ROD achieves state-of-art performance and is more robust for the graph sparsity.

cs.LG↗

arXiv2021

Fast Hyperparameter Optimization of Deep Neural Networks via Ensembling Multiple Surrogates

The performance of deep neural networks crucially depends on good hyperparameter configurations. Bayesian optimization is a powerful framework for optimizing the hyperparameters of DNNs. These methods need sufficient evaluation data to approximate and minimize the validation error function of hyperparameters. However, the expensive evaluation cost of DNNs leads to very few evaluation data within a limited time, which greatly reduces the efficiency of Bayesian optimization. Besides, the previous researches focus on using the complete evaluation data to conduct Bayesian optimization, and ignore the intermediate evaluation data generated by early stopping methods. To alleviate the insufficient evaluation data problem, we propose a fast hyperparameter optimization method, HOIST, that utilizes both the complete and intermediate evaluation data to accelerate the hyperparameter optimization of DNNs. Specifically, we train multiple basic surrogates to gather information from the mixed evaluation data, and then combine all basic surrogates using weighted bagging to provide an accurate ensemble surrogate. Our empirical studies show that HOIST outperforms the state-of-the-art approaches on a wide range of DNNs, including feed forward neural networks, convolutional neural networks, recurrent neural networks, and variational autoencoder.

cs.LG↗

arXiv2021

Extracting Governing Laws from Sample Path Data of Non-Gaussian Stochastic Dynamical Systems

Advances in data science are leading to new progresses in the analysis and understanding of complex dynamics for systems with experimental and observational data. With numerous physical phenomena exhibiting bursting, flights, hopping, and intermittent features, stochastic differential equations with non-Gaussian Lévy noise are suitable to model these systems. Thus it is desirable and essential to infer such equations from available data to reasonably predict dynamical behaviors. In this work, we consider a data-driven method to extract stochastic dynamical systems with non-Gaussian asymmetric (rather than the symmetric) Lévy process, as well as Gaussian Brownian motion. We establish a theoretical framework and design a numerical algorithm to compute the asymmetric Lévy jump measure, drift and diffusion (i.e., nonlocal Kramers-Moyal formulas), hence obtaining the stochastic governing law, from noisy data. Numerical experiments on several prototypical examples confirm the efficacy and accuracy of this method. This method will become an effective tool in discovering the governing laws from available data sets and in understanding the mechanisms underlying complex random phenomena.

math.ST↗

arXiv2021

VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition

End-to-end AutoML has attracted intensive interests from both academia and industry, which automatically searches for ML pipelines in a space induced by feature engineering, algorithm/model selection, and hyper-parameter tuning. Existing AutoML systems, however, suffer from scalability issues when applying to application domains with large, high-dimensional search spaces. We present VolcanoML, a scalable and extensible framework that facilitates systematic exploration of large AutoML search spaces. VolcanoML introduces and implements basic building blocks that decompose a large search space into smaller ones, and allows users to utilize these building blocks to compose an execution plan for the AutoML problem at hand. VolcanoML further supports a Volcano-style execution model - akin to the one supported by modern database systems - to execute the plan constructed. Our evaluation demonstrates that, not only does VolcanoML raise the level of expressiveness for search space decomposition in AutoML, it also leads to actual findings of decomposition strategies that are significantly more efficient than the ones employed by state-of-the-art AutoML systems such as auto-sklearn.

cs.LG↗

arXiv2021

MD Simulation of Hundred-Billion-Metal-Atom Cascade Collision on Sunway Taihulight

Radiation damage to the steel material of reactor pressure vessels is a major threat to the nuclear reactor safety. It is caused by the metal atom cascade collision, initialized when the atoms are struck by a high-energy neutron. The paper presents MISA-MD, a new implementation of molecular dynamics, to simulate such cascade collision with EAM potential. MISA-MD realizes (1) a hash-based data structure to efficiently store an atom and find its neighbors, and (2) several acceleration and optimization strategies based on SW26010 processor of Sunway Taihulight supercomputer, including an efficient potential table storage and interpolation method, a coloring method to avoid write conflicts, and double-buffer and data reuse strategies. The experimental results demonstrated that MISA-MD has good accuracy and scalability, and obtains a parallel efficiency of over 79% in an 655-billion-atom system. Compared with a state-of-the-art MD program LAMMPS, MISA-MD requires less memory usage and achieves better computational performance.

cs.DC↗

arXiv2021

Markov Blanket Discovery using Minimum Message Length

Causal discovery automates the learning of causal Bayesian networks from data and has been of active interest from their beginning. With the sourcing of large data sets off the internet, interest in scaling up to very large data sets has grown. One approach to this is to parallelize search using Markov Blanket (MB) discovery as a first step, followed by a process of combining MBs in a global causal model. We develop and explore three new methods of MB discovery using Minimum Message Length (MML) and compare them empirically to the best existing methods, whether developed specifically as MB discovery or as feature selection. Our best MML method is consistently competitive and has some advantageous features.

cs.LG↗

arXiv2021

Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach

Scenario generation is a fundamental and crucial tool for decision-making in power systems with high-penetration renewables. Based on big historical data, a novel federated deep generative learning framework, called Fed-LSGAN, is proposed by integrating federated learning and least square generative adversarial networks (LSGANs) for renewable scenario generation. Specifically, federated learning learns a shared global model in a central server from renewable sites at network edges, which enables the Fed-LSGAN to generate scenarios in a privacy-preserving manner without sacrificing the generation quality by transferring model parameters, rather than all data. Meanwhile, the LSGANs-based deep generative model generates scenarios that conform to the distribution of historical data through fully capturing the spatial-temporal characteristics of renewable powers, which leverages the least squares loss function to improve the training stability and generation quality. The simulation results demonstrate that the proposal manages to generate high-quality renewable scenarios and outperforms the state-of-the-art centralized methods. Besides, an experiment with different federated learning settings is designed and conducted to verify the robustness of our method.

cs.LG↗

arXiv2021

Coordinating Flexible Demand Response and Renewable Uncertainties for Scheduling of Community Integrated Energy Systems with an Electric Vehicle Charging Station: A Bi-level Approach

A community integrated energy system (CIES) with an electric vehicle charging station (EVCS) provides a new way for tackling growing concerns of energy efficiency and environmental pollution, it is a critical task to coordinate flexible demand response and multiple renewable uncertainties. To this end, a novel bi-level optimal dispatching model for the CIES with an EVCS in multi-stakeholder scenarios is established in this paper. In this model, an integrated demand response program is designed to promote a balance between energy supply and demand while maintaining a user comprehensive satisfaction within an acceptable range. To further tap the potential of demand response through flexibly guiding users' energy consumption and electric vehicles' behaviors (charging, discharging and providing spinning reserves), a dynamic pricing mechanism combining time-of-use and real-time pricing is put forward. In the solution phase, by using sequence operation theory (SOT), the original chance-constrained programming (CCP) model is converted into a readily solvable mixed-integer linear programming (MILP) formulation and finally solved by CPLEX solver. The simulation results on a practical CIES located in North China demonstrate that the presented method manages to balance the interests between CIES and EVCS via the coordination of flexible demand response and uncertain renewables.

eess.SY↗

arXiv2021

Dynamic State Estimation for Integrated Natural Gas and Electric Power Systems

A dynamic state estimation method of integrated natural gas and electric power systems (IGESs) in proposed. Firstly, the coupling model of gas pipeline networks and power systems by gas turbine units (GTUs) is established. Secondly, the Kalman filter based linear DSE model for the IGES is built. The gas density and mass flow rate, as well as the real and imaginary parts of bus voltages are taken as states, which are predicted by the linearized fluid dynamic equations of gases and exponential smoothing techniques. Boundary conditions of pipeline networks are used as supplementary constraints in the system model. At last, the proposed method is applied to an IGES including a 30-node pipeline network and IEEE 39-bus system coupled by two GTUs. Two indexes are used to evaluate the DSE performance under three measurement error conditions, and the results show that the DSE can obtain the accurate dynamic states in different conditions.

eess.SP↗

arXiv2021

Towards Robust Active Feature Acquisition

Truly intelligent systems are expected to make critical decisions with incomplete and uncertain data. Active feature acquisition (AFA), where features are sequentially acquired to improve the prediction, is a step towards this goal. However, current AFA models all deal with a small set of candidate features and have difficulty scaling to a large feature space. Moreover, they are ignorant about the valid domains where they can predict confidently, thus they can be vulnerable to out-of-distribution (OOD) inputs. In order to remedy these deficiencies and bring AFA models closer to practical use, we propose several techniques to advance the current AFA approaches. Our framework can easily handle a large number of features using a hierarchical acquisition policy and is more robust to OOD inputs with the help of an OOD detector for partially observed data. Extensive experiments demonstrate the efficacy of our framework over strong baselines.

cs.LG↗

arXiv2021

Attribute-aware Explainable Complementary Clothing Recommendation

Modelling mix-and-match relationships among fashion items has become increasingly demanding yet challenging for modern E-commerce recommender systems. When performing clothes matching, most existing approaches leverage the latent visual features extracted from fashion item images for compatibility modelling, which lacks explainability of generated matching results and can hardly convince users of the recommendations. Though recent methods start to incorporate pre-defined attribute information (e.g., colour, style, length, etc.) for learning item representations and improving the model interpretability, their utilisation of attribute information is still mainly reserved for enhancing the learned item representations and generating explanations via post-processing. As a result, this creates a severe bottleneck when we are trying to advance the recommendation accuracy and generating fine-grained explanations since the explicit attributes have only loose connections to the actual recommendation process. This work aims to tackle the explainability challenge in fashion recommendation tasks by proposing a novel Attribute-aware Fashion Recommender (AFRec). Specifically, AFRec recommender assesses the outfit compatibility by explicitly leveraging the extracted attribute-level representations from each item's visual feature. The attributes serve as the bridge between two fashion items, where we quantify the affinity of a pair of items through the learned compatibility between their attributes. Extensive experiments have demonstrated that, by making full use of the explicit attributes in the recommendation process, AFRec is able to achieve state-of-the-art recommendation accuracy and generate intuitive explanations at the same time.

cs.IR↗

arXiv2021

Virtual synchronous generator of PV generation without energy storage for frequency support in autonomous microgrid

In autonomous microgrids frequency regulation (FR) is a critical issue, especially with a high level of penetration of the photovoltaic (PV) generation. In this study, a novel virtual synchronous generator (VSG) control for PV generation was introduced to provide frequency support without energy storage. PV generation reserve a part of the active power in accordance with the pre-defined power versus voltage curve. Based on the similarities of the synchronous generator power-angle characteristic curve and the PV array characteristic curve, PV voltage Vpv can be analogized to the power angle δ. An emulated governor (droop control) and the swing equation control is designed and applied to the DC-DC converter. PV voltage deviation is subsequently generated and the pre-defined power versus voltage curve is modified to provide the primary frequency and inertia support. A simulation model of an autonomous microgrid with PV, storage, and diesel generator was built. The feasibility and effectiveness of the proposed VSG strategy are examined under different operating conditions.

eess.SY↗

arXiv2021

On convergence of numerical solutions for the compressible MHD system with exactly divergence-free magnetic field

We study a general convergence theory for the numerical solutions of compressible viscous and electrically conducting fluids with a focus on numerical schemes that preserve the divergence free property of magnetic field exactly. Our strategy utilizes the recent concepts of dissipative weak solutions and consistent approximations. First, we show the dissipative weak--strong uniqueness principle, meaning a dissipative weak solution coincides with a classical solution as long as they emanate from the same initial data. Next, we show the convergence of consistent approximation towards the dissipative weak solution and thus the classical solution. Upon interpreting the consistent approximation as the stability and consistency of suitable numerical solutions we have established a generalized Lax equivalence theory: convergence $\Longleftrightarrow$ stability and consistency. Further, to illustrate the application of this theory, we propose two novel mixed finite volume-finite element methods with exact divergence-free magnetic field. Finally, by showing solutions of these two schemes are consistent approximations, we conclude their convergence towards the dissipative weak solution and the classical solution.

math.NA↗

arXiv2021

Dep-$L_0$: Improving $L_0$-based Network Sparsification via Dependency Modeling

Training deep neural networks with an $L_0$ regularization is one of the prominent approaches for network pruning or sparsification. The method prunes the network during training by encouraging weights to become exactly zero. However, recent work of Gale et al. reveals that although this method yields high compression rates on smaller datasets, it performs inconsistently on large-scale learning tasks, such as ResNet50 on ImageNet. We analyze this phenomenon through the lens of variational inference and find that it is likely due to the independent modeling of binary gates, the mean-field approximation, which is known in Bayesian statistics for its poor performance due to the crude approximation. To mitigate this deficiency, we propose a dependency modeling of binary gates, which can be modeled effectively as a multi-layer perceptron (MLP). We term our algorithm Dep-$L_0$ as it prunes networks via a dependency-enabled $L_0$ regularization. Extensive experiments on CIFAR10, CIFAR100 and ImageNet with VGG16, ResNet50, ResNet56 show that our Dep-$L_0$ outperforms the original $L_0$-HC algorithm of Louizos et al. by a significant margin, especially on ImageNet. Compared with the state-of-the-arts network sparsification algorithms, our dependency modeling makes the $L_0$-based sparsification once again very competitive on large-scale learning tasks. Our source code is available at https://github.com/leo-yangli/dep-l0.

cs.LG↗