检索结果-内蒙古大学图书馆

Attention-Based Knowledge-aware Multi-Interest intelligent Model for Sequential Recommendation

学校读者我要写书评

暂无评论

Attention-Based Knowledge-aware Multi-Interest Intelligent M...

Symposia and Workshops on Ubiquitous, Autonomic and Trusted computing, UIC-ATC

作者： Yang Li Qianmu Li Shunmei Meng Jun Hou School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Intelligent Manufacturing Department Wuyi University Jiangmen China State Key Lab. for Novel Software Technology Nanjing University Nanjing China School of Social Science Nanjing Vocational University of Industry Technology Nanjing China

As a fundamental means of intelligent service, recommender systems have shown a trend of diversification. Sequential recommendation, a class of time-aware methods, aims to predict the user’s next click. Multi-interest representation is a hot topic in recommender systems, but the research on how to apply multi-interest into sequences is still in the minority. And many methods will introduce knowledge graph to improve the representation of items, but how to consider both knowledge graph and user’s multi-interest in sequential recommendation has become a temporary blank. In this paper, we propose an attentive sequential recommendation with knowledge-aware multi-interest module (AKAMI). Items are embedded from the sequence’s structure and user’s interests. Specifically, we represent items by stacking self-attention layers to mine the internal correlation of the sequence. Meanwhile, we segment the sequence via the common neighbors in the knowledge graph and cast the user’s multi-interest based on the aggregation of subsequences. Multi-interests are integrated into item representation by the gating network adaptively. Comprehensive experiments on two real-world datasets show that the proposed model performs better than various representative methods under different evaluation metrics. Additionally, we also visually explain the model through a case study.

关键词：

Bridge the Gap between Supervised and Unsupervised Learning for Fine-Grained Classification

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Jiabao Li, Yang Wei, Xiu-Shen Li, Hang Miao, Zhuang Zhang, Rui Army Engineering University of PLA Nanjing210007 China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing210094 China Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Lab. for Novel Software Technology Nanjing University Nanjing210023 China

Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID). However, it is found that the unsupervised learning of fine-grained visual classification (FGVC) is more challenging than GOC and person re-ID. In order to bridge the gap between unsupervised and supervised learning for FGVC, we investigate the essential factors (including feature extraction, clustering, and contrastive learning) for the performance gap between supervised and unsupervised FGVC. Furthermore, we propose a simple, effective, and practical method, termed as UFCL, to alleviate the gap. Three key issues are concerned and improved: First, we introduce a robust and powerful backbone, ResNet50-IBN, which has an ability of domain adaptation when we transfer ImageNet pre-trained models to FGVC tasks. Next, we propose to introduce HDBSCAN instead of DBSCAN to do clustering, which can generate better clusters for adjacent categories with fewer hyper-parameters. Finally, we propose a weighted feature agent and its updating mechanism to do contrastive learning by using the pseudo lab.ls with inevitable noise, which can improve the optimization process of learning the parameters of the network. The effectiveness of our UFCL is verified on CUB-200-2011, Oxford-Flowers, Oxford-Pets, Stanford-Dogs, Stanford-Cars and FGVC-Aircraft datasets. Under the unsupervised FGVC setting, we achieve state-of-the-art results, and analyze the key factors and the important parameters to provide a practical guidance. Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

The minority matters: a diversity-promoting collab.rative metric learning algorithm 22

学校读者我要写书评

暂无评论

The minority matters: a diversity-promoting collaborative me...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Shilong Bao Qianqian Xu Zhiyong Yang Yuan He Xiaochun Cao Qingming Huang State Key Laboratory of Information Security Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences Alibaba Group School of Cyber Science and Technology Shenzhen Campus Sun Yat-sen University Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management CAS and Peng Cheng Laboratory

ISBN: (纸本)9781713871088

Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collab.rative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity Control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.

关键词：

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficient Crowdsourcing for Video Analytics

学校读者我要写书评

暂无评论

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficien...

International Conference on Data engineering

作者： Yu Chen Sheng Zhang Ziying Zhou Xiaokun Wang Yu Liang Ning Chen Yuting Yan Mingjun Xiao Jie Wu Zhuzhong Qian Harry Xu State Key Lab. for Novel Software Technology Nanjing University P.R. China School of Systems Science Beijing Normal University China School of Computer and Electronic Information / School of Artificial Intelligence Nanjing Normal University China School of Computer Science and Technology University of Science and Technology of China P.R. China Center for Networked Computing Temple University USA Computer Science Department Samueli School of Engineering University of California Los Angeles USA

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

In recent years, many crowdsourcing platforms have emerged, using the resources of recruited workers to perform diverse outsourcing tasks, where the video analytics attracts much attention due to its practical implications. For maximum profits, platforms carefully choose the workers and determine the video analytics configurations to ensure accuracy; meanwhile, workers possess the flexibility to tailor the configurations for their indivi-dual gains, which makes it hard for platforms to optimize their profits considering the platform-worker conflicts. In this paper, we design an incentive mechanism for Multi-leader game-based video Analytics upon CROwdsourcing, named MACRO, to over-come the above situation. Under that mechanism, we first formu-late the utility optimization problems for platforms and workers, respectively. We then propose a dual ascent-based method to op-timally determine the video analytics configurations for a multi-platform game, ensuring Pareto efficiency. Moreover, in the context of a multi-leader game involving platform-worker conflicts, we design an incentive function with its incentive factor update strategy and propose an ADMM-based approach for maximizing incentives that motivate workers to contribute to the platforms' profits. Rigorous proofs demonstrate the linear convergence of the MACRO to the multi-leader Stackelberg equilibrium. Trace-driven experiments show that MACRO improves the Pareto efficiency by 26.3%, outperforming other approaches.

关键词： Crowdsourcing Accuracy Visual analytics Games Data engineering Outsourcing Task analysis

Explore Contextual Information for 3D Scene Graph Generation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Yuanyuan Long, Chengjiang Zhang, Zhaoxuan Liu, Bokai Zhang, Qiang Yin, Baocai Yang, Xin The Department of Electronic Information and Electrical Engineering Dalian University of Technology Dalian116024 China Meta Reality Labs BurlingameCA94010 United States The Key Lab of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China The Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Faculty of Information Technology Beijing University of Technology Beijing100124 China

3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation lab.l has been gradually improved, the performance of existing works is still far from being perfect for fine-grained and multi-lab.l situations. In this paper, we propose a framework fully exploring contextual information for the 3D SGG task, which attempts to satisfy the requirements of fine-grained entity class, multiple relation lab.ls, and high accuracy simultaneously. Our proposed approach is composed of a Graph Feature Extraction module and a Graph Contextual Reasoning module, achieving appropriate information-redundancy feature extraction, structured organization, and hierarchical inferring. Our approach achieves superior or competitive performance over previous methods on the 3DSSG dataset, especially on the relationship prediction sub-task. Copyright © 2022, The Authors. All rights reserved.

关键词： Feature extraction

UAV-Assisted Over-the-Air Computation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Fu, Min Zhou, Yong Shi, Yuanming Wang, Ting Chen, Wei School of Information Science and Technology ShanghaiTech University Shanghai201210 China Shanghai Key Lab. of Trustworthy Computing School of Software Engineering East China Normal University China Department of Electronic Engineering Tsinghua University Beijing100084 China

Over-the-air computation (AirComp) provides a promising way to support ultrafast aggregation of distributed data. However, its performance cannot be guaranteed in long-distance transmission due to the distortion induced by the channel fading and noise. To unleash the full potential of AirComp, this paper proposes to use a low-cost unmanned aerial vehicle (UAV) acting as a mobile base station to assist AirComp systems. Specifically, due to its controllab.e high-mobility and high-altitude, the UAV can move sufficiently close to the sensors to enable line-of-sight transmission and adaptively adjust all the links’ distances, thereby enhancing the signal magnitude alignment and noise suppression. Our goal is to minimize the time-averaging mean-square error for AirComp by jointly optimizing the UAV trajectory, the scaling factor at the UAV, and the transmit power at the sensors, under constraints on the UAV’s predetermined locations and flying speed, sensors’ average and peak power limits. However, due to the highly coupled optimization variables and time-dependent constraints, the resulting problem is non-convex and challenging. We thus propose an efficient iterative algorithm by applying the block coordinate descent and successive convex optimization techniques. Simulation results verify the convergence of the proposed algorithm and demonstrate the performance gains and robustness of the proposed design compared with benchmarks. © 2021, CC BY.

关键词： Unmanned aerial vehicles (UAV)

DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dai, Siran Xu, Qianqian Yang, Zhiyong Cao, Xiaochun Huang, Qingming SKLOIS Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Tech. CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China BDKM University of Chinese Academy of Sciences China

The Area Under the ROC Curve (AUC) is a widely employed metric in long-tailed classification scenarios. Nevertheless, most existing methods primarily assume that training and testing examples are drawn i.i.d. from the same distribution, which is often unachievable in practice. Distributionally Robust Optimization (DRO) enhances model performance by optimizing it for the local worst-case scenario, but directly integrating AUC optimization with DRO results in an intractable optimization problem. To tackle this challenge, methodically we propose an instance-wise surrogate loss of Distributionally Robust AUC (DRAUC) and build our optimization framework on top of it. Moreover, we highlight that conventional DRAUC may induce lab.l bias, hence introducing distribution-aware DRAUC as a more suitable metric for robust AUC learning. Theoretically, we affirm that the generalization gap between the training loss and testing error diminishes if the training set is sufficiently large. Empirically, experiments on corrupted benchmark datasets demonstrate the effectiveness of our proposed method. Code is availab.e at: https://***/EldercatSAM/DRAUC. © 2023, CC BY.

关键词： Optimization

A Many-Objective Evolutionary Algorithm Assisted by Ideal Hyperplane

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Zhang, Zhixia Wen, Jie Wang, Hui Cai, Xingjuan Cui, Zhihua Zhang, Wensheng School of Computer Science and Technology Taiyuan University of Science and Technology China School of Information Engineering Nanchang Institute of Technology Nanchang330099 China State Key Laboratory of Intelligent Control and Management of Complex System Institute of Automation Chinese Academy of Sciences China State Key Lab. for Novel Software Technology Nanjing University China

In many-objective optimization problems (MaOPs), it is a difficult task for evolutionary algorithms to balance convergence and diversity while rapidly converging to the Pareto front. As the number of objectives increases, the difficulty of evolutionary algorithms increases with individual selection pressure. To address above problems, we propose a many-objective evolution algorithm assisted by an ideal hyperplane (MaOEA-IH). Firstly, the ideal hyperplane as a reference surface to guide the individual to search the Pareto front, which is established from the extremum of each dimension of the objective space. Secondly, a parallel p -norm mating selection strategy is proposed to improve convergence. In addition, two factors are considered in this strategy: 1) different p -norm are used to measure different spatial scales;2) individual selection uncertainty is defined by incorporating a probabilistic perturbation mechanism. Thirdly, the improved shift-based density estimation strategy is used as the evaluation criterion for environmental selection to improve the convergence and diversity of solution sets and enhance selection pressure. To verify the effectiveness of the proposed algorithm, MAOEA-IH is compared with seven excellent algorithms in three benchmark sets (DTLZ, WFG and MaF). The results show that the proposed MAOEA-IH is highly competitive in solving MaOPs. © 2022, The Authors. All rights reserved.

关键词： Geometry

Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Zhuo Zhu, Miaoxi Xia, Xiaobo Shen, Li Yu, Jun Gong, Chen Han, Bo Du, Bo Liu, Tongliang Syndey Ai Centre The University of Sydney Australia National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Jd Explore Academy China Department of Automation University of Science and Technology of China China Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China Department of Computer Science Hong Kong Baptist University Hong Kong

Robust generalization aims to tackle the most challenging data distributions which are rare in the training set and contain severe noises, i.e., photon-limited corruptions. Common solutions such as distributionally robust optimization (DRO) focus on the worst-case empirical risk to ensure low training error on the uncommon noisy distributions. However, due to the over-parameterized model being optimized on scarce worst-case data, DRO fails to produce a smooth loss landscape, thus struggling on generalizing well to the test set. Therefore, instead of focusing on the worst-case risk minimization, we propose SharpDRO by penalizing the sharpness of the worst-case distribution, which measures the loss changes around the neighbor of learning parameters. Through worst-case sharpness minimization, the proposed method successfully produces a flat loss curve on the corrupted distributions, thus achieving robust generalization. Moreover, by considering whether the distribution annotation is availab.e, we apply SharpDRO to two problem settings and design a worst-case selection process for robust generalization. Theoretically, we show that SharpDRO has a great convergence guarantee. Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains. Copyright © 2023, The Authors. All rights reserved.

关键词： Optimization