相关论文: Dividable Configuration Performance Learning

Large scale deep learning provides a tremendous opportunity to improve the quality of content recommendation systems by employing both wider and deeper models, but this comes at great infrastructural cost and carbon footprint in modern data…

This paper presents meta-sparsity, a framework for learning model sparsity, basically learning the parameter that controls the degree of sparsity, that allows deep neural networks (DNNs) to inherently generate optimal sparse shared…

In many open environment applications, data are collected in the form of a stream, which exhibits an evolving distribution over time. How to design algorithms to track these evolving data distributions with provable guarantees, particularly…

Active learning is considered a viable solution to alleviate the contradiction between the high dependency of deep learning-based segmentation methods on annotated data and the expensive pixel-level annotation cost of medical images.…

Modern configurable systems provide tremendous opportunities for engineering future intelligent software systems. A key difficulty thereof is how to effectively self-adapt the configuration of a running system such that its performance…

Configurable software systems are employed in many important application domains. Understanding the performance of the systems under all configurations is critical to prevent potential performance issues caused by misconfiguration. However,…

Learning relational tabular data has gained significant attention recently, but most studies focus on single tables, overlooking the potential of cross-table learning. Cross-table learning, especially in scenarios where tables lack shared…

Performance predictors have emerged as a promising method to accelerate the evaluation stage of neural architecture search (NAS). These predictors estimate the performance of unseen architectures by learning from the correlation between a…

Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed. Common techniques such as re-sampling and cost-sensitive learning require prior-knowledge to train the system.…

Modern configurable software systems need to learn models that correlate configuration and performance. However, when the system operates in dynamic environments, the workload variations, hardware changes, and system updates will inevitably…

A key challenge in the continual learning setting is to efficiently learn a sequence of tasks without forgetting how to perform previously learned tasks. Many existing approaches to this problem work by either retraining the model on…

As the size of datasets used in statistical learning continues to grow, distributed training of models has attracted increasing attention. These methods partition the data and exploit parallelism to reduce memory and runtime, but suffer…

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a…

Diffusion models (DMs) are a powerful type of generative models that have achieved state-of-the-art results in various image synthesis tasks and have shown potential in other domains, such as natural language processing and temporal data…

Ensuring reliability in modern software systems requires rigorous pre-production testing across highly heterogeneous and evolving environments. Because exhaustive evaluation is infeasible, practitioners must decide how to allocate limited…

Learning predictive models from observations using deep neural networks (DNNs) is a promising new approach to many real-world planning and control problems. However, common DNNs are too unstructured for effective planning, and current…

Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. There is an emerging literature on tackling this problem by…

While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in an easy-to-hard manner and on the selected examples…

Despite many proposed algorithms to provide robustness to deep learning (DL) models, DL models remain susceptible to adversarial attacks. We hypothesize that the adversarial vulnerability of DL models stems from two factors. The first…

Standard deep learning relies on Backpropagation (BP), which is constrained by biologically implausible weight symmetry and suffers from significant gradient interference within dense representations. To mitigate these bottlenecks, we…