Searcharxiv⌕ Search

arXiv subjects

Miao Zhang

Publications and source records attributed to Miao Zhang.

At least 163 records · Page 9Linked to original sources
arXiv2023

ILCAS: Imitation Learning-Based Configuration-Adaptive Streaming for Live Video Analytics with Cross-Camera Collaboration

The high-accuracy and resource-intensive deep neural networks (DNNs) have been widely adopted by live video analytics (VA), where camera videos are streamed over the network to resource-rich edge/cloud servers for DNN inference. Common video encoding configurations (e.g., resolution and frame rate) have been identified with significant impacts on striking the balance between bandwidth consumption and inference accuracy and therefore their adaption scheme has been a focus of optimization. However, previous profiling-based solutions suffer from high profiling cost, while existing deep reinforcement learning (DRL) based solutions may achieve poor performance due to the usage of fixed reward function for training the agent, which fails to craft the application goals in various scenarios. In this paper, we propose ILCAS, the first imitation learning (IL) based configuration-adaptive VA streaming system. Unlike DRL-based solutions, ILCAS trains the agent with demonstrations collected from the expert which is designed as an offline optimal policy that solves the configuration adaption problem through dynamic programming. To tackle the challenge of video content dynamics, ILCAS derives motion feature maps based on motion vectors which allow ILCAS to visually ``perceive'' video content changes. Moreover, ILCAS incorporates a cross-camera collaboration scheme to exploit the spatio-temporal correlations of cameras for more proper configuration selection. Extensive experiments confirm the superiority of ILCAS compared with state-of-the-art solutions, with 2-20.9% improvement of mean accuracy and 19.9-85.3% reduction of chunk upload lag.

cs.NI↗
arXiv2023

GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels

Evaluating the performance of graph neural networks (GNNs) is an essential task for practical GNN model deployment and serving, as deployed GNNs face significant performance uncertainty when inferring on unseen and unlabeled test graphs, due to mismatched training-test graph distributions. In this paper, we study a new problem, GNN model evaluation, that aims to assess the performance of a specific GNN model trained on labeled and observed graphs, by precisely estimating its performance (e.g., node classification accuracy) on unseen graphs without labels. Concretely, we propose a two-stage GNN model evaluation framework, including (1) DiscGraph set construction and (2) GNNEvaluator training and inference. The DiscGraph set captures wide-range and diverse graph data distribution discrepancies through a discrepancy measurement function, which exploits the outputs of GNNs related to latent node embeddings and node class predictions. Under the effective training supervision from the DiscGraph set, GNNEvaluator learns to precisely estimate node classification accuracy of the to-be-evaluated GNN model and makes an accurate inference for evaluating GNN model performance. Extensive experiments on real-world unseen and unlabeled test graphs demonstrate the effectiveness of our proposed method for GNN model evaluation.

cs.LG↗
arXiv2023

Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data

Graph condensation, which reduces the size of a large-scale graph by synthesizing a small-scale condensed graph as its substitution, has immediate benefits for various graph learning tasks. However, existing graph condensation methods rely on the joint optimization of nodes and structures in the condensed graph, and overlook critical issues in effectiveness and generalization ability. In this paper, we advocate a new Structure-Free Graph Condensation paradigm, named SFGC, to distill a large-scale graph into a small-scale graph node set without explicit graph structures, i.e., graph-free data. Our idea is to implicitly encode topology structure information into the node attributes in the synthesized graph-free data, whose topology is reduced to an identity matrix. Specifically, SFGC contains two collaborative components: (1) a training trajectory meta-matching scheme for effectively synthesizing small-scale graph-free data; (2) a graph neural feature score metric for dynamically evaluating the quality of the condensed data. Through training trajectory meta-matching, SFGC aligns the long-term GNN learning behaviors between the large-scale graph and the condensed small-scale graph-free data, ensuring comprehensive and compact transfer of informative knowledge to the graph-free data. Afterward, the underlying condensed graph-free data would be dynamically evaluated with the graph neural feature score, which is a closed-form metric for ensuring the excellent expressiveness of the condensed graph-free data. Extensive experiments verify the superiority of SFGC across different condensation ratios.

cs.LG↗
arXiv2023

Asymmetrically Decentralized Federated Learning

To address the communication burden and privacy concerns associated with the centralized server in Federated Learning (FL), Decentralized Federated Learning (DFL) has emerged, which discards the server with a peer-to-peer (P2P) communication framework. However, most existing DFL algorithms are based on symmetric topologies, such as ring and grid topologies, which can easily lead to deadlocks and are susceptible to the impact of network link quality in practice. To address these issues, this paper proposes the DFedSGPSM algorithm, which is based on asymmetric topologies and utilizes the Push-Sum protocol to effectively solve consensus optimization problems. To further improve algorithm performance and alleviate local heterogeneous overfitting in Federated Learning (FL), our algorithm combines the Sharpness Aware Minimization (SAM) optimizer and local momentum. The SAM optimizer employs gradient perturbations to generate locally flat models and searches for models with uniformly low loss values, mitigating local heterogeneous overfitting. The local momentum accelerates the optimization process of the SAM optimizer. Theoretical analysis proves that DFedSGPSM achieves a convergence rate of $\mathcal{O}(\frac{1}{\sqrt{T}})$ in a non-convex smooth setting under mild assumptions. This analysis also reveals that better topological connectivity achieves tighter upper bounds. Empirically, extensive experiments are conducted on the MNIST, CIFAR10, and CIFAR100 datasets, demonstrating the superior performance of our algorithm compared to state-of-the-art optimizers.

cs.LG↗
arXiv2023

Deep Model Fusion: A Survey

Deep model fusion/merging is an emerging technique that merges the parameters or predictions of multiple deep learning models into a single one. It combines the abilities of different models to make up for the biases and errors of a single model to achieve better performance. However, deep model fusion on large-scale deep learning models (e.g., LLMs and foundation models) faces several challenges, including high computational cost, high-dimensional parameter space, interference between different heterogeneous models, etc. Although model fusion has attracted widespread attention due to its potential to solve complex real-world tasks, there is still a lack of complete and detailed survey research on this technique. Accordingly, in order to understand the model fusion method better and promote its development, we present a comprehensive survey to summarize the recent progress. Specifically, we categorize existing deep model fusion methods as four-fold: (1) "Mode connectivity", which connects the solutions in weight space via a path of non-increasing loss, in order to obtain better initialization for model fusion; (2) "Alignment" matches units between neural networks to create better conditions for fusion; (3) "Weight average", a classical model fusion method, averages the weights of multiple models to obtain more accurate results closer to the optimal solution; (4) "Ensemble learning" combines the outputs of diverse models, which is a foundational technique for improving the accuracy and robustness of the final model. In addition, we analyze the challenges faced by deep model fusion and propose possible research directions for model fusion in the future. Our review is helpful in deeply understanding the correlation between different model fusion methods and practical application methods, which can enlighten the research in the field of deep model fusion.

cs.LG↗
arXiv2023

Computational prediction of ideal strength for a material

The ideal strength is crucial for predicting material behavior under extreme conditions, which can provide insights into material limits, guide design and engineer for enhanced performance and durability. In this work, we present a method within an allows for the estimation of tensile, shear, and indentation strengths in any crystallographic direction or plane. We have examined the strain-stress relationships of several well-known structures and compared our findings with previous work, demonstrating the effectiveness of our approach. Moreover, we performed extensive investigations into the indentation strength of hexagonal WC, \b{eta}-SiC, and MgA$l_2O_4$. The current study uncovers the modes of structural deformation and the underlying atomistic mechanisms. The insights gained from this study have significant implications for the further exploration and design of superhard materials.

cond-mat.mtrl-sci↗
arXiv2023

Understanding User Behavior in Volumetric Video Watching: Dataset, Analysis and Prediction

Volumetric video emerges as a new attractive video paradigm in recent years since it provides an immersive and interactive 3D viewing experience with six degree-of-freedom (DoF). Unlike traditional 2D or panoramic videos, volumetric videos require dense point clouds, voxels, meshes, or huge neural models to depict volumetric scenes, which results in a prohibitively high bandwidth burden for video delivery. Users' behavior analysis, especially the viewport and gaze analysis, then plays a significant role in prioritizing the content streaming within users' viewport and degrading the remaining content to maximize user QoE with limited bandwidth. Although understanding user behavior is crucial, to the best of our best knowledge, there are no available 3D volumetric video viewing datasets containing fine-grained user interactivity features, not to mention further analysis and behavior prediction. In this paper, we for the first time release a volumetric video viewing behavior dataset, with a large scale, multiple dimensions, and diverse conditions. We conduct an in-depth analysis to understand user behaviors when viewing volumetric videos. Interesting findings on user viewport, gaze, and motion preference related to different videos and users are revealed. We finally design a transformer-based viewport prediction model that fuses the features of both gaze and motion, which is able to achieve high accuracy at various conditions. Our prediction model is expected to further benefit volumetric video streaming optimization. Our dataset, along with the corresponding visualization tools is accessible at https://cuhksz-inml.github.io/user-behavior-in-vv-watching/

cs.MM↗
arXiv2023

Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining

A challenge of channel pruning is designing efficient and effective criteria to select channels to prune. A widely used criterion is minimal performance degeneration. To accurately evaluate the truth performance degeneration requires retraining the survived weights to convergence, which is prohibitively slow. Hence existing pruning methods use previous weights (without retraining) to evaluate the performance degeneration. However, we observe the loss changes differ significantly with and without retraining. It motivates us to develop a technique to evaluate true loss changes without retraining, with which channels to prune can be selected more reliably and confidently. We first derive a closed-form estimator of the true loss change per pruning mask change, using influence functions without retraining. Influence function which is from robust statistics reveals the impacts of a training sample on the model's prediction and is repurposed by us to assess impacts on true loss changes. We then show how to assess the importance of all channels simultaneously and develop a novel global channel pruning algorithm accordingly. We conduct extensive experiments to verify the effectiveness of the proposed algorithm. To the best of our knowledge, we are the first that shows evaluating true loss changes for pruning without retraining is possible. This finding will open up opportunities for a series of new paradigms to emerge that differ from existing pruning methods. The code is available at https://github.com/hrcheng1066/IFSO.

cs.CV↗
arXiv2023

OBSTransformer: A Deep-Learning Seismic Phase Picker for OBS Data Using Automated Labelling and Transfer Learning

Accurate seismic phase detection and onset picking are fundamental to seismological studies. Supervised deep-learning phase pickers have shown promise with excellent performance on land seismic data. Although it may be acceptable to apply them to OBS (Ocean Bottom Seismometers) data that are indispensable for studying ocean regions, they suffer from a significant performance drop. In this study, we develop a generalised transfer-learned OBS phase picker - OBSTransformer, based on automated labelling and transfer learning. First, we compile a comprehensive dataset of catalogued earthquakes recorded by 423 OBSs from 11 temporary deployments worldwide. Through automated processes, we label the P and S phases of these earthquakes by analysing the consistency of at least three arrivals from four widely used machine learning pickers (EqTransformer, PhaseNet, Generalized Phase Detection, and PickNet), as well as the AIC picker. This results in an inclusive OBS dataset containing ~36,000 earthquake samples. Subsequently, we employ this dataset for transfer learning and utilize a well-trained land machine learning model - EqTransformer as our base model. Moreover, we extract 25,000 OBS noise samples from the same OBS networks using the Kurtosis method, which are then used for model training alongside the labelled earthquake samples. Using three groups of test datasets at sub-global, regional, and local scales, we demonstrate that OBSTransformer outperforms EqTransformer. Particularly, the P and S recall rates at large distances (>200 km) are increased by 68% and 76%, respectively. Our extensive tests and comparisons demonstrate that OBSTransformer is less dependent on the detection/picking thresholds and is more robust to noise levels.

physics.geo-ph↗
arXiv2023

Physics-Assisted Reduced-Order Modeling for Identifying Dominant Features of Transonic Buffet

Transonic buffet is a flow instability phenomenon that arises from the interaction between the shock wave and the separated boundary layer. This flow phenomenon is considered to be highly detrimental during flight and poses a significant risk to the structural strength and fatigue life of aircraft. Up to now, there has been a lack of an accurate, efficient, and intuitive metric to predict buffet and impose a feasible constraint on aerodynamic design. In this paper, a Physics-Assisted Variational Autoencoder (PAVAE) is proposed to identify dominant features of transonic buffet, which combines unsupervised reduced-order modeling with additional physical information embedded via a buffet classifier. Specifically, four models with various weights adjusting the contribution of the classifier are trained, so as to investigate the impact of buffet information on the latent space. Statistical results reveal that buffet state can be determined exactly with just one latent space when a proper weight of classifier is chosen. The dominant latent space further reveals a strong relevance with the key flow features located in the boundary layers downstream of shock. Based on this identification, the displacement thickness at 80% chordwise location is proposed as a metric for buffet prediction. This metric achieves an accuracy of 98.5% in buffet state classification, which is more reliable than the existing separation metric used in design. The proposed method integrates the benefits of feature extraction, flow reconstruction, and buffet prediction into a unified framework, demonstrating its potential in low-dimensional representations of high-dimensional flow data and interpreting the "black box" neural network.

physics.flu-dyn↗
arXiv2023

SCRNet: a Retinex Structure-based Low-light Enhancement Model Guided by Spatial Consistency

Images captured under low-light conditions are often plagued by several challenges, including diminished contrast, increased noise, loss of fine details, and unnatural color reproduction. These factors can significantly hinder the performance of computer vision tasks such as object detection and image segmentation. As a result, improving the quality of low-light images is of paramount importance for practical applications in the computer vision domain.To effectively address these challenges, we present a novel low-light image enhancement model, termed Spatial Consistency Retinex Network (SCRNet), which leverages the Retinex-based structure and is guided by the principle of spatial consistency.Specifically, our proposed model incorporates three levels of consistency: channel level, semantic level, and texture level, inspired by the principle of spatial consistency.These levels of consistency enable our model to adaptively enhance image features, ensuring more accurate and visually pleasing results.Extensive experimental evaluations on various low-light image datasets demonstrate that our proposed SCRNet outshines existing state-of-the-art methods, highlighting the potential of SCRNet as an effective solution for enhancing low-light images.

cs.CV↗
arXiv2023

Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis

The recently proposed training-free NAS methods abandon the training phase and design various zero-cost proxies as scores to identify excellent architectures, arousing extreme computational efficiency for neural architecture search. In this paper, we raise an interesting problem: can we properly measure the operation importance in DARTS through a training-free way, with avoiding the parameter-intensive bias? We investigate this question through the lens of edge connectivity, and provide an affirmative answer by defining a connectivity concept, ZERo-cost Operation Sensitivity (ZEROS), to score the importance of candidate operations in DARTS at initialization. By devising an iterative and data-agnostic manner in utilizing ZEROS for NAS, our novel trial leads to a framework called training free differentiable architecture search (FreeDARTS). Based on the theory of Neural Tangent Kernel (NTK), we show the proposed connectivity score provably negatively correlated with the generalization bound of DARTS supernet after convergence under gradient descent training. In addition, we theoretically explain how ZEROS implicitly avoids parameter-intensive bias in selecting architectures, and empirically show the searched architectures by FreeDARTS are of comparable size. Extensive experiments have been conducted on a series of search spaces, and results have demonstrated that FreeDARTS is a reliable and efficient baseline for neural architecture search.

cs.LG↗
arXiv2023

Parametric Generative Schemes with Geometric Constraints for Encoding and Synthesizing Airfoils

The modern aerodynamic optimization has a strong demand for parametric methods with high levels of intuitiveness, flexibility, and representative accuracy, which cannot be fully achieved through traditional airfoil parametric techniques. In this paper, two deep learning-based generative schemes are proposed to effectively capture the complexity of the design space while satisfying specific constraints. 1. Soft-constrained scheme: a Conditional Variational Autoencoder (CVAE)-based model to train geometric constraints as part of the network directly. 2. Hard-constrained scheme: a VAE-based model to generate diverse airfoils and an FFD-based technique to project the generated airfoils onto the given constraints. According to the statistical results, the reconstructed airfoils are both accurate and smooth, without any need for additional filters. The soft-constrained scheme generates airfoils that exhibit slight deviations from the expected geometric constraints, yet still converge to the reference airfoil in both geometry space and objective space with some degree of distribution bias. In contrast, the hard-constrained scheme produces airfoils with a wider range of geometric diversity while strictly adhering to the geometric constraints. The corresponding distribution in the objective space is also more diverse, with isotropic uniformity around the reference point and no significant bias. These proposed airfoil parametric methods can break through the boundaries of training data in the objective space, providing higher quality samples for random sampling and improving the efficiency of optimization design.

physics.flu-dyn↗
arXiv2023

Prediction of transonic flow over supercritical airfoils using geometric-encoding and deep-learning strategies

The Reynolds-averaged Navier-Stokes equation for compressible flow over supercritical airfoils under various flow conditions must be rapidly and accurately solved to shorten design cycles for such airfoils. Although deep-learning methods can effectively predict flow fields, the accuracy of these predictions near sensitive regions and their generalizability to large-scale datasets in engineering applications must be enhanced. In this study, a modified vision transformer-based encoder-decoder network is designed for the prediction of transonic flow over supercritical airfoils. In addition, four methods are designed to encode the geometric input with various information points and the performances of these methods are compared. The statistical results show that these methods generate accurate predictions over the complete flow field, with a mean absolute error on the order of 1e-4. To increase accuracy near the shock area, multilevel wavelet transformation and gradient distribution losses are introduced into the loss function. This results in the maximum error that is typically observed near the shock area decreasing by 50%. Furthermore, the models are pretrained through transfer learning on large-scale datasets and finetuned on small datasets to improve their generalizability in engineering applications. The results generated by various pretrained models demonstrate that transfer learning yields a comparable accuracy from a reduced training time.

physics.flu-dyn↗
arXiv2023

Knowledge-embedded meta-learning model for lift coefficient prediction of airfoils

Aerodynamic performance evaluation is an important part of the aircraft aerodynamic design optimization process; however, traditional methods are costly and time-consuming. Despite the fact that various machine learning methods can achieve high accuracy, their application in engineering is still difficult due to their poor generalization performance and "black box" nature. In this paper, a knowledge-embedded meta learning model, which fully integrates data with the theoretical knowledge of the lift curve, is developed to obtain the lift coefficients of an arbitrary supercritical airfoil under various angle of attacks. In the proposed model, a primary network is responsible for representing the relationship between the lift and angle of attack, while the geometry information is encoded into a hyper network to predict the unknown parameters involved in the primary network. Specifically, three models with different architectures are trained to provide various interpretations. Compared to the ordinary neural network, our proposed model can exhibit better generalization capability with competitive prediction accuracy. Afterward, interpretable analysis is performed based on the Integrated Gradients and Saliency methods. Results show that the proposed model can tend to assess the influence of airfoil geometry to the physical characteristics. Furthermore, the exceptions and shortcomings caused by the proposed model are analysed and discussed in detail.

physics.flu-dyn↗
arXiv2023

Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting

Sensors in cyber-physical systems often capture interconnected processes and thus emit correlated time series (CTS), the forecasting of which enables important applications. The key to successful CTS forecasting is to uncover the temporal dynamics of time series and the spatial correlations among time series. Deep learning-based solutions exhibit impressive performance at discerning these aspects. In particular, automated CTS forecasting, where the design of an optimal deep learning architecture is automated, enables forecasting accuracy that surpasses what has been achieved by manual approaches. However, automated CTS solutions remain in their infancy and are only able to find optimal architectures for predefined hyperparameters and scale poorly to large-scale CTS. To overcome these limitations, we propose SEARCH, a joint, scalable framework, to automatically devise effective CTS forecasting models. Specifically, we encode each candidate architecture and accompanying hyperparameters into a joint graph representation. We introduce an efficient Architecture-Hyperparameter Comparator (AHC) to rank all architecture-hyperparameter pairs, and we then further evaluate the top-ranked pairs to select a final result. Extensive experiments on six benchmark datasets demonstrate that SEARCH not only eliminates manual efforts but also is capable of better performance than manually designed and existing automatically designed CTS models. In addition, it shows excellent scalability to large CTS.

cs.LG↗
arXiv2023

LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version

Due to the sweeping digitalization of processes, increasingly vast amounts of time series data are being produced. Accurate classification of such time series facilitates decision making in multiple domains. State-of-the-art classification accuracy is often achieved by ensemble learning where results are synthesized from multiple base models. This characteristic implies that ensemble learning needs substantial computing resources, preventing their use in resource-limited environments, such as in edge devices. To extend the applicability of ensemble learning, we propose the LightTS framework that compresses large ensembles into lightweight models while ensuring competitive accuracy. First, we propose adaptive ensemble distillation that assigns adaptive weights to different base models such that their varying classification capabilities contribute purposefully to the training of the lightweight model. Second, we propose means of identifying Pareto optimal settings w.r.t. model accuracy and model size, thus enabling users with a space budget to select the most accurate lightweight model. We report on experiments using 128 real-world time series sets and different types of base models that justify key decisions in the design of LightTS and provide evidence that LightTS is able to outperform competitors.

cs.LG↗
arXiv2023

Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs

Graph neural architecture search (NAS) has gained popularity in automatically designing powerful graph neural networks (GNNs) with relieving human efforts. However, existing graph NAS methods mainly work under the homophily assumption and overlook another important graph property, i.e., heterophily, which exists widely in various real-world applications. To date, automated heterophilic graph learning with NAS is still a research blank to be filled in. Due to the complexity and variety of heterophilic graphs, the critical challenge of heterophilic graph NAS mainly lies in developing the heterophily-specific search space and strategy. Therefore, in this paper, we propose a novel automated graph neural network on heterophilic graphs, namely Auto-HeG, to automatically build heterophilic GNN models with expressive learning abilities. Specifically, Auto-HeG incorporates heterophily into all stages of automatic heterophilic graph learning, including search space design, supernet training, and architecture selection. Through the diverse message-passing scheme with joint micro-level and macro-level designs, we first build a comprehensive heterophilic GNN search space, enabling Auto-HeG to integrate complex and various heterophily of graphs. With a progressive supernet training strategy, we dynamically shrink the initial search space according to layer-wise variation of heterophily, resulting in a compact and efficient supernet. Taking a heterophily-aware distance criterion as the guidance, we conduct heterophilic architecture selection in the leave-one-out pattern, so that specialized and expressive heterophilic GNN architectures can be derived. Extensive experiments illustrate the superiority of Auto-HeG in developing excellent heterophilic GNNs to human-designed models and graph NAS models.

cs.LG↗