检索结果-内蒙古大学图书馆

Residual K-Nearest Neighbors Label Distribution Learning

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Wang, Jing Geng, Xin School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China

Label Distribution Learning (LDL) is a novel learning paradigm that assigns label distribution to each instance. It aims to learn the label distribution of training instances and predict unknown ones. Algorithm Adaptation (AA)-kNN is one of the most representative LDL baselines that adapts the kNN algorithm to LDL. Its generalization risk has been proven to approach zero if given infinite training data. Despite its theoretical advantage, AA-kNN generally performs poorly because real-world LDL problems only have finite or small training data. In this paper, we improve AA-kNN and propose a novel method called Residual k-Nearest Neighbors Label Distribution Learning (RkNN-LDL). First, RkNN-LDL introduces residual label distribution learning. Second, RkNN-LDL exploits the neighborhood structure of label distribution. We prove that RkNN-LDL has an O( [[EQUATION]] ) generalization bound. Besides, extensive experiments validate that RkNN-LDL beats several state-of-the-art LDL methods and statistically outperforms AA-NN. © 2023, The Authors. All rights reserved.

关键词： Nearest neighbor search

TPMARL-MSS Thought-Perception Multi-Agent Reinforcement Learning Meeting Scheduling System 25

学校读者我要写书评

暂无评论

TPMARL-MSS Thought-Perception Multi-Agent Reinforcement Lear...

25th IEEE International Conferences on High Performance Computing and Communications, 9th International Conference on Data Science and Systems, 21st IEEE International Conference on Smart City and 9th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Applications, HPCC/DSS/SmartCity/DependSys 2023

作者： Zhang, Jinsong Mao, Xiaoxuan Li, Lu Wu, Hanqian Joint Graduate School Southeast University Nanjing China College of Software Engineering Southeast University Nanjing China School of Cyber Science and Engineering Southeast University Nanjing China School of Cyber Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration of Ministry of Education Nanjing China

ISBN: (纸本)9798350330014

In today's evolving society, the increasing complexity and frequency of meetings necessitate advanced scheduling systems. Traditional methods are constrained by rigid prede-fined strategies, lack intelligent negotiation mechanisms, and often compromise user privacy. Addressing these challenges, we introduce the Thought-Perception Multi-Agent Reinforcement Learning Meeting Scheduling System (TPMARL-MSS). Unlike conventional systems, TPMARL-MSS autonomously learns and refines its strategies through continuous feedback. It features automated negotiation and adaptive decision-making, offering a more nuanced scheduling approach. Importantly, our Thought-Perception module protect privacy, allowing the agent to deduce preferences from participant behavior without revealing personal data. Evaluations on the real-world dataset shows that TPMARL-MSS surpasses traditional methods in efficiency and schedule quality, highlighting its practical applicability. © 2023 IEEE.

关键词： Decision making

Adiabatic-Passage-Based Parameter Setting for Quantum Approximate Optimization Algorithm

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Mingyou Chen, Hanwu School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing211189 China

The Quantum Approximate Optimization Algorithm (QAOA) exhibits significant potential for tackling combinatorial optimization problems. Despite its promise for near-term quantum devices, a major challenge in applying QAOA lies in the cost of circuit runs associated with parameter optimization. Existing methods for parameter setting generally incur at least a superlinear cost concerning the depth p of QAOA. In this study, we propose a novel adiabatic-passage-based parameter setting method that remarkably reduces the optimization cost, specifically when applied to the 3-SAT problem, to a sublinear level. Beginning with an analysis of the random model of the specific problem, this method applies a problem-dependent preprocessing on the problem Hamiltonian analytically, effectively segregating the magnitude of parameters from the scale of the problem. Consequently, a problem-independent initialization is achieved without incurring any optimization cost or pre-computation. Furthermore, the parameter space is adjusted based on the continuity of the optimal adiabatic passage, resulting in a reduction in the disparity of parameters between adjacent layers of QAOA. By leveraging this continuity, the cost to find quasi-optimal parameters is significantly reduced to a sublinear level. © 2023, CC BY.

关键词： Combinatorial optimization

Inaccurate Label Distribution Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kou, Zhiqiang Jia, Yuheng Wang, Jing Geng, Xin The School of Computer Science and Engineering Southeast University Nanjing211189 China The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing211189 China

Label distribution learning (LDL) trains a model to predict the relevance of a set of labels (called label distribution (LD)) to an instance. The previous LDL methods all assumed the LDs of the training instances are accurate. However, annotating highly accurate LDs for training instances is time-consuming and very expensive, and in reality the collected LD is usually inaccurate and disturbed by annotating errors. For the first time, this paper investigates the problem of inaccurate LDL, i.e., developing an LDL model with noisy LDs. We assume that the noisy LD matrix is a linear combination of an ideal LD matrix and a sparse noise matrix. Consequently, the problem of inaccurate LDL becomes an inverse problem, where the objective is to recover the ideal LD and noise matrices from the noisy LDs. We hypothesize that the ideal LD matrix is low-rank due to the correlation of labels and utilize the local geometric structure of instances captured by a graph to assist in recovering the ideal LD. This is based on the premise that similar instances are likely to share the same LD. The proposed model is finally formulated as a graph-regularized low-rank and sparse decomposition problem and numerically solved by the alternating direction method of multipliers. Furthermore, a specialized objective function is utilized to induce a LD predictive model in LDL, taking into account the recovered label distributions. Extensive experiments conducted on multiple datasets from various real-world tasks effectively demonstrate the efficacy of the proposed approach. Copyright © 2023, The Authors. All rights reserved.

关键词： Inverse problems

Deep Convolutional Dictionary Learning network for Sparse View Ct Reconstruction with a Group Sparse Prior

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Kang, Yanqin Liu, Jin Wu, Fan Wang, Kun Qiang, Jun Hu, Dianlin Zhang, Yikun College of Computer and Information Anhui Polytechnic University Wuhu China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

Purpose: Many deep learning-based methods have been applied in sparse view computed tomography (CT) imaging. However, most methods are built intuitively using state-of-the-art black-box convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields, neglecting nonlocal self-similarity prior information. How to obtain diagnostically useful images from sparsely sampled projections is a challenging, ill-posed ***: To address this issue, we propose a novel interpretable model based on a convolutional dictionary learning network and nonlocal group sparse prior, called DCDL-GS, for sparse view CT image reconstruction. We apply a statistical iterative reconstruction algorithm for a fixed number of iterations with a neural network to improve the image reconstruction quality. Inspired by a group sparsity prior, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Additionally, filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight convolutional dictionary learning network are integrated into our DCDL-GS model, improving model ***: The visual results based on the LDCT-P and UIH datasets show the efficiency of our proposed DCDL-GS model in edge preservation and feature recovery. The quantitative results show improvement over state-of-the-art methods, with improvements of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) based on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse ***: We developed a unified optimized mathematical model incorporating projection data and image prior knowled

关键词： Image reconstruction

On accuracy rate of community detection and pairing in mobile social network

学校读者我要写书评

暂无评论

On accuracy rate of community detection and pairing in mobil...

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

作者： Jinbin Tu Qing Li Yun Wang School of Computer Science and Engineering Southeast University Key Lab of Computer Network and Information Integration Nanjing MOE China

Mobile Social network(MSN) is an opportunity network that considers the social attributes of nodes, and also uses the ”store-carry-forward” model to carry out data transfer between nodes. The community nature of nodes is an important reference in MSN to select messaging path. In this paper, a new community cluster problem based on our observed pickup strategies for car-hailing is proposed, which is involving community detection and community pairing. Then we formulate it by using T-Sorokin mobility model. The Cluster-First algorithm and Pair-First algorithm are proposed based on the defined community dependency metric to maximize the accuracy rate. Simulation experimental results show that both CFA and PFA can effectively solve this problem with an accuracy rate of over 70%. And it is concluded that cluster-first is superior to pair-first for this considered problem.

关键词：

SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Zeng Zhang, Linhai Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which might fail in a training-from-scratch setting where no source-domain data is used. To tackle training-from-scratch setting, it is crucial to make full use of the annotation information (the boundaries and entity types). Therefore, in this paper, we propose a novel multitask (Seed, Expand and Entail) learning framework, SEE-Few, for Few-shot NER without using source domain data. The seeding and expanding modules are responsible for providing as accurate candidate spans as possible for the entailing module. The entailing module reformulates span classification as a textual entailment task, leveraging both the contextual clues and entity type information. All the three modules share the same text encoder and are jointly learned. Experimental results on four benchmark datasets under the training-from-scratch setting show that the proposed method outperformed state-of-the-art few-shot NER methods with a large margin. Copyright © 2022, The Authors. All rights reserved.

关键词： Classification (of information)

Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Si, Jiasheng Zhu, Yingjie Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the performance of prediction drops dramatically when being removed. Though being explainable, most rationale extraction methods for multi-hop fact verification explore the semantic information within each piece of evidence individually, while ignoring the topological information interaction among different pieces of evidence. Intuitively, a faithful rationale bears complementary information being able to extract other rationales through the multi-hop reasoning process. To tackle such disadvantages, we cast explainable multi-hop fact verification as subgraph extraction, which can be solved based on graph convolutional network (GCN) with salience-aware graph learning. In specific, GCN is utilized to incorporate the topological interaction information among multiple pieces of evidence for learning evidence representation. Meanwhile, to alleviate the influence of noisy evidence, the salience-aware graph perturbation is induced into the message passing of GCN. Moreover, the multi-task model with three diagnostic properties of rationale is elaborately designed to improve the quality of an explanation without any explicit annotations. Experimental results on the FEVEROUS benchmark show significant gains over previous state-of-the-art methods for both rationale extraction and fact verification. Copyright © 2022, The Authors. All rights reserved.

关键词： Message passing

Continuous contrastive learning for long-tailed semi-supervised recognition 24

学校读者我要写书评

暂无评论

Continuous contrastive learning for long-tailed semi-supervi...

Proceedings of the 38th International Conference on Neural information Processing Systems

作者： Zi-Hao Zhou Siyuan Fang Zi-Jing Zhou Tong Wei Yuanyu Wan Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China Xiaomi Inc. China School of Software Technology Zhejiang University Ningbo China

ISBN: (纸本)9798331314385

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality pseudo-labels for large-scale unlabeled data. However, these methods often neglect the impact of representations learned by the neural network and struggle with real-world unlabeled data, which typically follows a different distribution than labeled data. This paper introduces a novel probabilistic framework that unifies various recent proposals in long-tail learning. Our framework derives the class-balanced contrastive loss through Gaussian kernel density estimation. We introduce a continuous contrastive learning method, CCL, extending our framework to unlabeled data using reliable and smoothed pseudo-labels. By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios. Extensive experiments across multiple datasets with varying unlabeled data distributions demonstrate that CCL consistently outperforms prior state-of-the-art methods, achieving over 4% improvement on the ImageNet-127 dataset. Our source code is available at https://***/zhouzihao11/CCL.

关键词：