arXiv subjects

Haochuan Cui

Publications and source records attributed to Haochuan Cui.

6 recordsLinked to original sources

arXiv2025

Scalable Reinforcement Learning for Virtual Machine Scheduling

Recent advancements in reinforcement learning (RL) have shown promise for optimizing virtual machine scheduling (VMS) in small-scale clusters. The utilization of RL to large-scale cloud computing scenarios remains notably constrained. This paper introduces a scalable RL framework, called Cluster Value Decomposition Reinforcement Learning (CVD-RL), to surmount the scalability hurdles inherent in large-scale VMS. The CVD-RL framework innovatively combines a decomposition operator with a look-ahead operator to adeptly manage representation complexities, while complemented by a Top-$k$ filter operator that refines exploration efficiency. Different from existing approaches limited to clusters of $10$ or fewer physical machines (PMs), CVD-RL extends its applicability to environments encompassing up to $50$ PMs. Furthermore, the CVD-RL framework demonstrates generalization capabilities that surpass contemporary SOTA methodologies across a variety of scenarios in empirical studies. This breakthrough not only showcases the framework's exceptional scalability and performance but also represents a significant leap in the application of RL for VMS within complex, large-scale cloud infrastructures. The code is available at https://anonymous.4open.science/r/marl4sche-D0FE.

cs.LG↗

arXiv2023

Breaking the Boundaries of Knowledge Space: Analyzing the Knowledge Spanning on the Q&A Website through Word Embeddings

The challenge of raising a creative question exists in recombining different categories of knowledge. However, the impact of recombination remains controversial. Drawing on the theories of knowledge recombination and category spanning, we propose that both the distance of knowledge spanning and the hierarchy of knowledge shape the appeal of questions. Using word embedding models and the data collected from a large online knowledge market (N = 463,545), we find that the impact of knowledge spanning on the appeal of questions is parabolic: the appeal of questions increases up to a threshold, after which point the positive effect reverses. However, the nonlinear influence of knowledge spanning is contingent upon the hierarchy of knowledge. The theoretical and practical implications of these findings for future research on knowledge recombination are discussed. We fill the research gap by conceptualizing question asking as knowledge spanning and highlighting the theoretical underpinnings of the knowledge hierarchy.

cs.SI↗

arXiv2023

Unpacking the Essential Tension of Knowledge Recombination: Analyzing the Impact of Knowledge Spanning on Citation Counts and Disruptive Innovation

Drawing on the theories of knowledge recombination, we aim to unpack the essential tension between tradition and innovation in scientific research. Using the American Physical Society data and computational methods, we analyze the impact of knowledge spanning on both citation counts and disruptive innovation. The findings show that knowledge spanning has a U-shaped impact on disruptive innovation. In contrast, there is an inverted U-shaped relationship between knowledge spanning and citation counts, and the inverted U-shaped effect is moderated by team size. This study contributes to the theories of knowledge recombination by suggesting that both intellectual conformism and knowledge recombination can lead to disruptive innovation. That is, when evaluating the quality of scientific research with disruptive innovation, the essential tension seems to disappear.

cs.SI↗

arXiv2022

ReAssigner: A Plug-and-Play Virtual Machine Scheduling Intensifier for Heterogeneous Requests

With the rapid development of cloud computing, virtual machine scheduling has become one of the most important but challenging issues for the cloud computing community, especially for practical heterogeneous request sequences. By analyzing the impact of request heterogeneity on some popular heuristic schedulers, it can be found that existing scheduling algorithms can not handle the request heterogeneity properly and efficiently. In this paper, a plug-and-play virtual machine scheduling intensifier, called Resource Assigner (ReAssigner), is proposed to enhance the scheduling efficiency of any given scheduler for heterogeneous requests. The key idea of ReAssigner is to pre-assign roles to physical resources and let resources of the same role form a virtual cluster to handle homogeneous requests. ReAssigner can cooperate with arbitrary schedulers by restricting their scheduling space to virtual clusters. With evaluations on the real dataset from Huawei Cloud, the proposed ReAssigner achieves significant scheduling performance improvement compared with some state-of-the-art scheduling methods.

cs.DC↗

arXiv2022

Aging and the Narrowing of Scientific Innovation

With rising life expectancies around the world and an older scientific workforce than ever before, what does aging mean for individual scientists, and what do aging scientists mean for scientific progress as a whole? Here we examine how scientists and scholars age in terms of how their ideas and contributions relate to the evolving frontier of knowledge and how demographically aging fields relate to field-level advance. At the individual level, we examine how research experiences and choices can moderate the effects of intellectual aging. At the collective level, we explore mechanisms that link individual and collective aging. Prior research focuses on star scientists, their changing dates and rates of breakthrough success throughout history. We explore this for scientists in all fields over time, drawing upon novel deep learning measurements that allow us not only to trace positive attention through citation but also negative attention through explicit criticism with a novel, comprehensive database of over 20,000 human-validated critical citations. We find that younger scientists tend toward disruptive contributions that push the frontier, while older scientists engage in combinatorial innovation with an aging collection of components. This includes analyzing the impact of the 1994 U.S. Supreme Court ruling on mandatory retirement and examining how unexpected collaborations affect citation patterns.

cs.DL↗

arXiv2021

VMAgent: Scheduling Simulator for Reinforcement Learning

A novel simulator called VMAgent is introduced to help RL researchers better explore new methods, especially for virtual machine scheduling. VMAgent is inspired by practical virtual machine (VM) scheduling tasks and provides an efficient simulation platform that can reflect the real situations of cloud computing. Three scenarios (fading, recovering, and expansion) are concluded from practical cloud computing and corresponds to many reinforcement learning challenges (high dimensional state and action spaces, high non-stationarity, and life-long demand). VMAgent provides flexible configurations for RL researchers to design their customized scheduling environments considering different problem features. From the VM scheduling perspective, VMAgent also helps to explore better learning-based scheduling solutions.

cs.LG↗