检索结果-内蒙古大学图书馆

LECF: recommendation via learnable edge collaborative filtering

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第1期65卷 116-130页

作者： Shitao XIAO Yingxia SHAO Yawen LI Hongzhi YIN Yanyan SHEN Bin CUI School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing Key Lab of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications School of Information Technology and Electrical Engineering The University of Queensland Department of Computer Science and Engineering Shanghai Jiao Tong University Department of Computer Science and Technology Peking University National Engineering Laboratory for Big Data Analysis and Applications Peking University

The core of recommendation models is estimating the probability that a user will like an item based on historical interactions. Existing collaborative filtering(CF) algorithms compute the likelihood by utilizing simple relationships between objects, e.g., user-item, item-item, or user-user. They always rely on a single type of object-object relationship, ignoring other useful relationship information in data. In this paper, we model an interaction between user and item as an edge and propose a novel CF framework, called learnable edge collaborative filtering(LECF). LECF predicts the existence probability of an edge based on the connections among edges and is able to capture the complex relationship in data. Specifically, we first adopt the concept of line graph where each node represents an interaction edge; then calculate a weighted sum of similarity between the query edge and the observed edges(i.e., historical interactions) that are selected from the neighborhood of query edge in the line graph for a recommendation. In addition, we design an efficient propagation algorithm to speed up the training and inference of LECF. Extensive experiments on four public datasets demonstrate LECF can achieve better performance than the state-of-the-art methods.

关键词： collaborative filtering recommender system implicit feedback edge-edge similarity line graph

ZOOMER: Boosting Retrieval on Web-scale Graphs by Regions of Interest

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Yuezihan Cheng, Yu Zhao, Hanyu Zhang, Wentao Miao, Xupeng He, Yu Wang, Liang Yang, Zhi Cui, Bin School of Software and Microelectronics Peking University China School of CS Key Laboratory of High Confidence Software Technologies Peking University China Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications China Alibaba Group China

We introduce ZOOMER, a system deployed at Taobao, the largest e-commerce platform in China, for training and serving GNN-based recommendations over web-scale graphs. ZOOMER is designed for tackling two challenges presented by the massive user data at Taobao: low training/serving efficiency due to the huge scale of the graphs, and low recommendation quality due to the information overload which distracts the recommendation model from specific user intentions. ZOOMER achieves this by introducing a key concept, Region of Interests (ROI) in GNNs for recommendations, i.e., a neighborhood region in the graph with significant relevance to a strong user intention. ZOOMER narrows the focus from the whole graph and "zooms in" on the more relevant ROIs, thereby reducing the training/serving cost and mitigating the information overload at the same time. With carefully designed mechanisms, ZOOMER identifies the interest expressed by each recommendation request, constructs an ROI subgraph by sampling with respect to the interest, and guides the GNN to reweigh different parts of the ROI towards the interest by a multi-level attention module. Deployed as a large-scale distributed system, ZOOMER supports graphs with billions of nodes for training and thousands of requests per second for serving. ZOOMER achieves up to 14x speedup when downsizing sampling scales with comparable (even better) AUC performance than baseline methods. Besides, both the offline evaluation and online A/B test demonstrate the effectiveness of ZOOMER. Copyright © 2022, The Authors. All rights reserved.

关键词： Graphic methods

Zero-Order Optimization in Security Constrained Power System Scheduling 4

学校读者我要写书评

暂无评论

Zero-Order Optimization in Security Constrained Power System...

4th IEEE International Conference on Electrical, Computer, and Energy Technologies, ICECET 2024

作者： An, Qi Wang, Jianxiao Wu, Shengyu Ren, Weikai Huang, Ruanming Li, Gengyin North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources Beijing China Peking University National Engineering Laboratory for Big Data Analysis and Applications Beijing China State Grid Energy Research Institute CO. LTD. Beijing China Institute of Energy Peking University Beijing China Planning Center State Grid Shanghai Electric Power Company Shanghai China

ISBN: (纸本)9798350395914

The security and resilience of power systems are gradually challenged. As a typical index measuring the security and resilience of power systems, the frequency stability issue is becoming prominent. Due to the increase in the complexity of power systems, the frequency stability boundary is gradually becoming fuzzy, leading to traditional analytical-modeling algorithms hardly applicable for frequency stability constrained dispatch. Existing data-driven methods for characterizing frequency stability boundary typically requires massive simulation calculations, leading to unnecessary computing power consumption. To this end, zeroth-order (ZO) optimization, which aims to solve optimization problems embedding non-analytic functions, is adopted for solving the frequency stability constrained dispatch in this paper. In contrast to traditional data-driven methods, we directly embed frequency stability simulation check into power system dispatch. The gradient of frequency stability simulation check is estimated through ZO optimization, thereby realizing the interaction optimization between power system dispatch and real-time simulation. In this way, the solution for the frequency stability constrained dispatch is modified towards the optimal point along the gradient descent direction. Cases studies based on IEEE-9 bus system verifies that, compared with traditional data-driven methods, the solution approach we propose could reduce the system cost while significantly improving the calculation efficiency. © 2024 IEEE.

关键词： Frequency stability

Rethinking Node-wise Propagation for Large-scale Graph Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Xunkai Su, Daohan Ma, Jingyuan Zhang, Wentao Wu, Zhengyu Li, Rong-Hua Wang, Guoren Beijing Institute of Technology Beijing China Peking University National Engineering Laboratory for Big Data Analytics and Applications Beijing China

Scalable graph neural networks (GNNs) have emerged as a promising technique, which exhibits superior predictive performance and high running efficiency across numerous large-scale graph-based web applications. However, (i) Most scalable GNNs tend to treat all nodes with the same propagation rules, neglecting their topological uniqueness;(ii) Existing node-wise propagation optimization strategies are insufficient on web-scale graphs with intricate topology, where a full portrayal of nodes’ local properties is required. Intuitively, different nodes in web-scale graphs possess distinct topological roles, and therefore propagating them indiscriminately or neglect local contexts may compromise the quality of node representations. To address the above issues, we propose Adaptive Topology-aware Propagation (ATP), which reduces potential high-bias propagation and extracts structural patterns of each node in a scalable manner to improve running efficiency and predictive performance. Remarkably, ATP is crafted to be a plug-and-play node-wise propagation optimization strategy, allowing for offline execution independent of the graph learning process in a new perspective. Therefore, this approach can be seamlessly integrated into most scalable GNNs while remain orthogonal to existing node-wise propagation optimization strategies. Extensive experiments on 12 datasets have demonstrated the effectiveness of ATP. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

Graph Attention Multi-Layer Perceptron

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Wentao Yin, Ziqi Sheng, Zeang Li, Yang Ouyang, Wen Li, Xiaosen Tao, Yangyu Yang, Zhi Cui, Bin School of CS & Key Laboratory of High Confidence Software Technologies Peking University China Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications China Tencent Inc China Beijing Institute of Technology China

Graph neural networks (GNNs) have achieved great success in many graph-based applications. However, the enormous size and high sparsity level of graphs hinder their applications under industrial scenarios. Although some scalable GNNs are proposed for large-scale graphs, they adopt a fixed k-hop neighborhood for each node, thus facing the over-smoothing issue when adopting large propagation depths for nodes within sparse regions. To tackle the above issue, we propose a new GNN architecture — Graph Attention Multi-Layer Perceptron (GAMLP), which can capture the underlying correlations between different scales of graph knowledge. We have deployed GAMLP in Tencent with the Angel platform 1, and we further evaluate GAMLP on both real-world datasets and large-scale industrial datasets. Extensive experiments on these 14 graph datasets demonstrate that GAMLP achieves state-of-the-art performance while enjoying high scalability and efficiency. Specifically, it outperforms GAT by 1.3% regarding predictive accuracy on our large-scale Tencent Video dataset while achieving up to 50× training speedup. Besides, it ranks top-1 on both the leader-boards of the largest homogeneous and heterogeneous graph (i.e., ogbn-papers100M and ogbn-mag) of Open Graph Benchmark 2 Copyright © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

Towards Dynamic and Safe Configuration Tuning for Cloud databases

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhang, Xinyi Wu, Hong Li, Yang Tan, Jian Li, Feifei Cui, Bin School of CS Key Laboratory of High Confidence Software Technologies Peking University China Database and Storage Laboratory Damo Academy Alibaba Group China Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications China China

Configuration knobs of database systems are essential to achieve high throughput and low latency. Recently, automatic tuning systems using machine learning methods (ML) have shown to find better configurations compared to experienced database administrators (DBAs). However, there are still gaps to apply the existing systems in production environments, especially in the cloud. First, they conduct tuning for a given workload within a limited time window and ignore the dynamicity of workloads and data. Second, they rely on a copied instance and do not consider the availability of the database when sampling configurations, making the tuning expensive, delayed, and unsafe. To fill these gaps, we propose OnlineTune, which tunes the online databases safely in changing cloud environments. To accommodate the dynamicity, OnlineTune embeds the environmental factors as context feature and adopts contextual Bayesian Optimization with context space partition to optimize the database adaptively and scalably. To pursue safety during tuning, we leverage the black-box and the white-box knowledge to evaluate the safety of configurations and propose a safe exploration strategy via subspace adaptation. We conduct evaluations on dynamic workloads from benchmarks and real-world workloads. Compared with the state-of-the-art methods, OnlineTune achieves 14.4%∼165.3% improvement on cumulative performance while reducing 91.0%∼99.5% unsafe configuration recommendations. Copyright © 2022, The Authors. All rights reserved.

关键词： database systems

A regularized approach to sparse optimal policy in reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Xiang Yang, Wenhao Zhang, Zhihua School of Mathematical Sciences Peking University Beijing China Center for Data Science Peking University Beijing China National Engineering Lab for Big Data Analysis and Applications School of Mathematical Sciences Peking University Beijing China

We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant entropy-regularized MDPs can be cast into our framework. Moreover, under our framework, many regularization terms can bring multi-modality and sparsity, which are potentially useful in reinforcement learning. In particular, we present sufficient and necessary conditions that induce a sparse optimal policy. We also conduct a full mathematical analysis of the proposed regularized MDPs, including the optimality condition, performance error, and sparseness control. We provide a generic method to devise regularization forms and propose off-policy actor critic algorithms in complex environment settings. We empirically analyze the numerical properties of optimal policies and compare the performance of different sparse regularization forms in discrete and continuous environments. Copyright © 2019, The Authors. All rights reserved.

关键词： Markov processes

Battery Valuation and Management for Battery Swapping Station with an Intertemporal Framework

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Xinjiang Yang, Yu Wang, Jianxiao Song, Jie He, Guannan College of Engineering Peking University Beijing100091 China Department of Industrial and Systems Engineering University of Florida GainesvilleFL116595 United States National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing100091 China

Battery swapping as a business model for battery energy storage (BES) has great potential in future integrated low-carbon energy and transportation systems. However, frequent battery swapping will inevitably accelerate battery degradation and shorten the battery life accordingly. To model the tradeoff of BES use between energy and transportation applications coupled by battery swapping, we develop a life-cycle decision model that coordinates battery charging and swapping. This model is derived based on an improved intertemporal decision framework, in which the optimal marginal degradation cost (MDC) of BES is determined to maximize the BES benefit across time and application. The proposed framework and model are applied to manage a battery swapping station that simultaneously provides battery swapping services to electric vehicle customers and provides flexibility service to the power grid, including energy arbitrage and reserve. The case study shows that while the end of the physical life of BES occurs faster with battery swapping, the economic life becomes considerably longer. The results also reveal that the optimal MDC depends on the battery values in each application, and we analyze how the battery swapping price affects the optimal MDC and battery life. The proposed framework and model can also provide decision support for on-demand BES service, such as battery trading, renting and secondary use. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision support systems

C olumnSGD: A Column-oriented Framework for Distributed Stochastic Gradient Descent

学校读者我要写书评

暂无评论

C olumnSGD: A Column-oriented Framework for Distributed Stoc...

International Conference on data engineering

作者： Zhipeng Zhang Wentao Wu Jiawei Jiang Lele Yu Bin Cui Ce Zhang School of EECS & Key Laboratory of High Confidence Software Technologies (MOE) Peking University Microsoft Research Redmond USA ETH Zurich Switzerland Tencent Inc Center for Data Science Peking University & National Engineering Laboratory for Big Data Analysis and Applications

ISBN: (数字)9781728129037

ISBN: (纸本)9781728129044

Distributed machine learning (ML) has triggered tremendous research interest in recent years. Stochastic gradient descent (SGD) is one of the most popular algorithms for training ML models, and has been implemented in almost all distributed ML systems, such as Spark MLlib, Petuum, MXNet, and TensorFlow. However, current implementations often incur huge communication and memory overheads when it comes to large models. One important reason for this inefficiency is the row-oriented scheme (RowSGD) that existing systems use to partition the training data, which forces them to adopt a centralized model management strategy that leads to vast amount of data exchange over the network. We propose a novel, column-oriented scheme (ColumnSGD) that partitions training data by columns rather than by rows. As a result, ML model can be partitioned by columns as well, leading to a distributed configuration where individual data and model partitions can be collocated on the same machine. Following this locality property, we develop a simple yet powerful computation framework that significantly reduces communication overheads and memory footprints compared to RowSGD, for large-scale ML models such as generalized linear models (GLMs) and factorization machines (FMs). We implement ColumnSGD on top of Apache Spark, and study its performance both analytically and experimentally. Experimental results on both public and real-world datasets show that ColumnSGD is up to 930× faster than MLlib, 63× faster than Petuum, and 14× faster than MXNet.

关键词： Conferences data engineering Radio frequency