Neural Radiance Fields (NeRF) have emerged as a powerful paradigm for 3D scene representation, offering high-fidelity renderings and reconstructions from a set of sparse and unstructured sensor data. In the context of...
详细信息
Neural Radiance Field (NeRF) has emerged as a powerful paradigm for scene representation, offering high-fidelity renderings and reconstructions from a set of sparse and unstructured sensor data. In the context of auto...
详细信息
Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despit...
Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB.
Within the realm of 6G Internet of Vehicles (6G-IoV), Federated Learning (FL) has become a notable machine learning framework, providing a decentralized method to protect data privacy while allowing cooperative model ...
详细信息
Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potent...
详细信息
Test of macroscopic realism (MR) is key to understanding the foundation of quantum mechanics. Due to the existence of the non-invasive measurability loophole and other interpretation loopholes, however, such test rema...
详细信息
We propose a robust estimation procedure based on local Walsh-average regression(LWR) for single-index models. Our novel method provides a root-n consistent estimate of the single-index parameter under some mild regul...
详细信息
We propose a robust estimation procedure based on local Walsh-average regression(LWR) for single-index models. Our novel method provides a root-n consistent estimate of the single-index parameter under some mild regularity conditions;the estimate of the unknown link function converges at the usual rate for the nonparametric estimation of a univariate covariate. We theoretically demonstrate that the new estimators show significant efficiency gain across a wide spectrum of non-normal error distributions and have almost no loss of efficiency for the normal error. Even in the worst case, the asymptotic relative efficiency(ARE) has a lower bound compared with the least squares(LS) estimates;the lower bounds of the AREs are 0.864 and 0.8896 for the single-index parameter and nonparametric function, respectively. Moreover, the ARE of the proposed LWR-based approach versus the ARE of the LS-based method has an expression that is closely related to the ARE of the signed-rank Wilcoxon test as compared with the t-test. In addition, to obtain a sparse estimate of the single-index parameter, we develop a variable selection procedure by combining the estimation method with smoothly clipped absolute deviation penalty;this procedure is shown to possess the oracle property. We also propose a Bayes information criterion(BIC)-type criterion for selecting the tuning parameter and further prove its ability to consistently identify the true model. We conduct some Monte Carlo simulations and a real data analysis to illustrate the finite sample performance of the proposed methods.
The robustness of deep neural network (DNN) is critical and challenging to ensure. In this paper, we propose a general data-oriented mutation framework, called Styx, to improve the robustness of DNN. Styx generates ne...
详细信息
ISBN:
(数字)9781450367684
ISBN:
(纸本)9781728172811
The robustness of deep neural network (DNN) is critical and challenging to ensure. In this paper, we propose a general data-oriented mutation framework, called Styx, to improve the robustness of DNN. Styx generates new training data by slightly mutating the training data. In this way, Styx ensures the DNN's accuracy on the test dataset while improving the adaptability to small perturbations, i.e., improving the robustness. We have instantiated Styx for image classification and proposed pixel-level mutation rules that are applicable to any image classification DNNs. We have applied Styx on several commonly used benchmarks and compared Styx with the representative adversarial training methods. The preliminary experimental results indicate the effectiveness of Styx.
Message passing is the primary programming paradigm in high-performancecomputing. However, developing message passing programs is challenging due to the non-determinism caused by parallel execution and complex progra...
详细信息
ISBN:
(数字)9781450371223
ISBN:
(纸本)9781728165288
Message passing is the primary programming paradigm in high-performancecomputing. However, developing message passing programs is challenging due to the non-determinism caused by parallel execution and complex programming features such as non-deterministic communications and asynchrony. We present MPI-SV, a symbolic verifier for verifying the parallel C programs using message passing interface (MPI). MPI-SV combines symbolic execution and model checking in a synergistic manner to improve the scalability and enlarge the scope of verifiable properties. We have applied MPI-SV to real-world MPI C programs. The experimental results indicate that MPI-SV can, on average, achieve 19x speedups in verifying deadlock-freedom and 5x speedups in finding counter-examples. MPI-SV can be accessed at https://***, and the demonstration video is at https://***/zzCY0CPDNCw.
Constraint solving is one of the challenges for symbolic execution. Modern SMT solvers allow users to customize the internal solving procedure by solving strategies. In this extended abstract, we report our recent pro...
详细信息
ISBN:
(数字)9781450367684
ISBN:
(纸本)9781728172811
Constraint solving is one of the challenges for symbolic execution. Modern SMT solvers allow users to customize the internal solving procedure by solving strategies. In this extended abstract, we report our recent progress in synthesizing a program-specific solving strategy for the symbolic execution of a program. We propose a two-stage procedure for symbolic execution. At the first stage, we synthesize a solving strategy by utilizing deep learning techniques. Then, the strategy will be used in the second stage to improve the performance of constraint solving. The preliminary experimental results indicate the promising of our method.
暂无评论