Search

Partial Label Learning (PLL) is a typical weakly supervised learning task, which assumes each training instance is annotated with a set of candidate labels containing the ground-truth label. Recent PLL methods adopt identification-based disambiguation to alleviate the influence of false positive labels and achieve promising performance. However, they require all classes in the test set to have appeared in the training set, ignoring the fact that new classes will keep emerging in real applications. To address this issue, in this paper, we focus on the problem of Partial Label Learning with Augmented Class (PLLAC), where one or more augmented classes are not visible in the training stage but appear in the inference stage. Specifically, we propose an unbiased risk estimator with theoretical guarantees for PLLAC, which estimates the distribution of augmented classes by differentiating the distribution of known classes from unlabeled data and can be equipped with arbitrary PLL loss functions. Besides, we provide a theoretical analysis of the estimation error bound of the estimator, which guarantees the convergence of the empirical risk minimizer to the true risk minimizer as the number of training data tends to infinity. Furthermore, we add a risk-penalty regularization term in the optimization objective to alleviate the influence of the over-fitting issue caused by negative empirical risk. Extensive experiments on benchmark, UCI and real-world datasets demonstrate the effectiveness of the proposed approach., Comment: 17 pages

As semiconductor power density is no longer constant with the technology process scaling down, modern CPUs are integrating capable data accelerators on chip, aiming to improve performance and efficiency for a wide range of applications and usages. One such accelerator is the Intel Data Streaming Accelerator (DSA) introduced in Intel 4th Generation Xeon Scalable CPUs (Sapphire Rapids). DSA targets data movement operations in memory that are common sources of overhead in datacenter workloads and infrastructure. In addition, it becomes much more versatile by supporting a wider range of operations on streaming data, such as CRC32 calculations, delta record creation/merging, and data integrity field (DIF) operations. This paper sets out to introduce the latest features supported by DSA, deep-dive into its versatility, and analyze its throughput benefits through a comprehensive evaluation. Along with the analysis of its characteristics, and the rich software ecosystem of DSA, we summarize several insights and guidelines for the programmer to make the most out of DSA, and use an in-depth case study of DPDK Vhost to demonstrate how these guidelines benefit a real application., Comment: This paper has been accepted by ASPLOS'24. Please refer to the linked DOI for the official version of this paper

Chiral edge modes inherent to the topological quantum anomalous Hall (QAH) effect are a pivotal topic of contemporary condensed matter research aiming at future quantum technology and application in spintronics. A large topological gap is vital to protecting against thermal fluctuations and thus enabling a higher operating temperature. From first-principle calculations, we propose Al$_{2}$O$_{3}$ as an ideal substrate for atomic monolayers consisting of Bi and group-III elements, in which a large-gap quantum spin Hall effect can be realized. Additional half-passivation with nitrogen then suggests a topological phase transition to a large-gap QAH insulator. By effective tight-binding modelling, we demonstrate that Bi-III monolayer/Al$_{2}$O$_{3}$ is dominated by $p_{x}, p_{y}$ orbitals, with subdominant $p_z$ orbital contributions. The topological phase transition into the QAH is induced by Zeeman splitting, where the off-diagonal spin exchange does not play a significant role. The effective model analysis promises utility far beyond Bi-III monolayer/Al$_{2}$O$_{3}$, as it should generically apply to systems dominated by $p_{x}, p_{y}$ orbitals with a band inversion at $\Gamma$., Comment: 9 pages with 4 figures