scholarly journals Self-Supervised Deep Low-Rank Assignment Model for Prototype Selection

2018 ◽  
Author(s):  
Xingxing Zhang ◽  
Zhenfeng Zhu ◽  
Yao Zhao ◽  
Deqiang Kong
Keyword(s):  
Large Scale ◽  
Task Assignment ◽  
Representation Learning ◽  
Low Rank ◽  
Prototype Selection ◽  
Weak Supervision ◽  
Large Scale Data ◽  
Assignment Model ◽  
Uncertain Distribution ◽  
Task Assignment Problem

Prototype selection is a promising technique for removing redundancy and irrelevance from large-scale data. Here, we consider it as a task assignment problem, which refers to assigning each element of a source set to one representative, i.e., prototype. However, due to the outliers and uncertain distribution on source, the selected prototypes are generally less representative and interesting. To alleviate this issue, we develop in this paper a Self-supervised Deep Low-rank Assignment model (SDLA). By dynamically integrating a low-rank assignment model with deep representation learning, our model effectively ensures the goodness-of-exemplar and goodness-of-discrimination of selected prototypes. Specifically, on the basis of a denoising autoencoder, dissimilarity metrics on source are continuously self-refined in embedding space with weak supervision from selected prototypes, thus preserving categorical similarity. Conversely, working on this metric space, similar samples tend to select the same prototypes by designing a low-rank assignment model. Experimental results on applications like text clustering and image classification (using prototypes) demonstrate our method is considerably superior to the state-of-the-art methods in prototype selection.

An Applicative Survey on Few-Shot Learning

2021 ◽  
Vol 15 ◽  
Author(s):  
Jianwei Zhang ◽  
Xubin Zhang ◽  
Lei Lv ◽  
Yining Di ◽  
Wei Chen
Keyword(s):  
Large Scale ◽  
Representation Learning ◽  
Language Models ◽  
Data Sets ◽  
Research Directions ◽  
Large Scale Data ◽  
Cross Domain ◽  
Meta Learning ◽  
Definition Of ◽  
Future Work

Background: Learning discriminative representation from large-scale data sets has made a breakthrough in decades. However, it is still a thorny problem to generate representative embedding from limited examples, for example, a class containing only one image. Recently, deep learning-based Few-Shot Learning (FSL) has been proposed. It tackles this problem by leveraging prior knowledge in various ways. Objective: In this work, we review recent advances of FSL from the perspective of high-dimensional representation learning. The results of the analysis can provide insights and directions for future work. Methods: We first present the definition of general FSL. Then we propose a general framework for the FSL problem and give the taxonomy under the framework. We survey two FSL directions: learning policy and meta-learning. Results: We review the advanced applications of FSL, including image classification, object detection, image segmentation and other tasks etc., as well as the corresponding benchmarks to provide an overview of recent progress. Conclusion: FSL needs to be further studied in medical images, language models, and reinforcement learning in future work. In addition, cross-domain FSL, successive FSL, and associated FSL are more challenging and valuable research directions.

A Hybrid Swarm Optimization Algorithm for Complex Assignment Problem

2010 ◽  
Vol 26-28 ◽  
pp. 1151-1154
Author(s):  
Zong Li Liu ◽  
Jie Cao ◽  
Zhan Ting Yuan
Keyword(s):  
Assignment Problem ◽  
Production Scheduling ◽  
Large Scale ◽  
Optimization Problems ◽  
Graph Model ◽  
Task Assignment ◽  
Hybrid Swarm ◽  
Swarm Optimization ◽  
Computing Technique ◽  
Task Assignment Problem

The optimization of complex systems, such as production scheduling systems and control systems, often encounters some difficulties, such as large-scale, hard to model, time consuming to evaluate, NP-hard, multi-modal, uncertain and multi-objective, etc. It is always a hot research topic in academic and engineering fields to propose advanced theory and effective algorithms. As a novel evolutionary computing technique, particle swarm optimization (PSO) is characterized by not being limited by the representation of the optimization problems, and by global optimization ability, which has gained wide attentation and research from both academic and industry fields. The task assignment problem in the enterprise with directed graph model is presented. Task assignment problem with buffer zone is solved via a hybrid PSO algorithm. Simulation result shows that the model and the algorithm are effective to the problem.

scholarly journals Hierarchical Task Assignment Strategy for Heterogeneous Multi-UAV System in Large-Scale Search and Rescue Scenarios

2021 ◽  
Vol 2021 ◽  
pp. 1-19
Author(s):  
Jie Chen ◽  
Kai Xiao ◽  
Kai You ◽  
Xianguo Qing ◽  
Fang Ye ◽  
...  
Keyword(s):  
Large Scale ◽  
Cluster Head ◽  
Task Assignment ◽  
Search And Rescue ◽  
Small Scale ◽  
Assignment Strategy ◽  
Negotiation Mechanism ◽  
Decoupling Algorithm ◽  
Task Assignment Problem ◽  
Multi Uav

For the large-scale search and rescue (S&R) scenarios, the centralized and distributed multi-UAV multitask assignment algorithms for multi-UAV systems have the problems of heavy computational load and massive communication burden, which make it hard to guarantee the effectiveness and convergence speed of their task assignment results. To address this issue, this paper proposes a hierarchical task assignment strategy. Firstly, a model decoupling algorithm based on density clustering and negotiation mechanism is raised to decompose the large-scale task assignment problem into several nonintersection and complete small-scale task assignment problems, which effectively reduces the required computational amount and communication cost. Then, a cluster head selection method based on multiattribute decision is put forward to select the cluster head for each UAV team. These cluster heads will communicate with the central control station about the latest assignment information to guarantee the completion of S&R mission. At last, considering that a few targets cannot be effectively allocated due to UAVs’ limited and unbalanced resources, an auction-based task sharing scheme among UAV teams is presented to guarantee the mission coverage of the multi-UAV system. Simulation results and analyses comprehensively verify the feasibility and effectiveness of the proposed hierarchical task assignment strategy in large-scale S&R scenarios with dispersed clustering targets.

scholarly journals An Evaluation of Supervised Dimensionality Reduction For Large Scale Data

2022 ◽  
pp. 17-25
Author(s):  
Nancy Jan Sliper
Keyword(s):  
Dimensionality Reduction ◽  
Large Scale ◽  
Simulated Data ◽  
Principal Component ◽  
Low Rank ◽  
Learning Tools ◽  
Large Scale Data ◽  
Reduction Methods ◽  
Low Dimensional ◽  
Scale Data

Experimenters today frequently quantify millions or even billions of characteristics (measurements) each sample to address critical biological issues, in the hopes that machine learning tools would be able to make correct data-driven judgments. An efficient analysis requires a low-dimensional representation that preserves the differentiating features in data whose size and complexity are orders of magnitude apart (e.g., if a certain ailment is present in the person's body). While there are several systems that can handle millions of variables and yet have strong empirical and conceptual guarantees, there are few that can be clearly understood. This research presents an evaluation of supervised dimensionality reduction for large scale data. We provide a methodology for expanding Principal Component Analysis (PCA) by including category moment estimations in low-dimensional projections. Linear Optimum Low-Rank (LOLR) projection, the cheapest variant, includes the class-conditional means. We show that LOLR projections and its extensions enhance representations of data for future classifications while retaining computing flexibility and reliability using both experimental and simulated data benchmark. When it comes to accuracy, LOLR prediction outperforms other modular linear dimension reduction methods that require much longer computation times on conventional computers. LOLR uses more than 150 million attributes in brain image processing datasets, and many genome sequencing datasets have more than half a million attributes.

scholarly journals A Grasshopper Optimization-Based Approach for Task Assignment in Cloud Logistics

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Lan Xu ◽  
Yiliu Tu ◽  
Yuting Zhang
Keyword(s):  
Large Scale ◽  
Programming Model ◽  
Task Assignment ◽  
Operational Mode ◽  
Assignment Model ◽  
Simulation Results ◽  
Grasshopper Optimization ◽  
Integrated Logistics ◽  
And Task ◽  
Biobjective Programming

A framework for the algorithm-based CL platform is established, based on which, the operational mode of it is described in detail. An integrated logistics task assignment model is built to optimally match logistics service resources and task of large scale in the algorithm-based CL. Particularly, an improved grasshopper optimization-based bitarget optimization algorithm (GROBO) is proposed to solve the biobjective programming model for service matching in CL. The case of Linyi small commodity logistics is taken as an application. Simulation results show that the proposed GROBO provides better solutions regarding to searching efficiency and stability in solving the model.

A Hybrid Algorithm for Task Assignment Problem in Holonic Manufacturing System

2010 ◽  
Vol 20-23 ◽  
pp. 1060-1065 ◽  
Author(s):  
Fu Qing Zhao ◽  
Jian Hua Zou ◽  
Shang Xiong Sheng
Keyword(s):  
Assignment Problem ◽  
Manufacturing System ◽  
Task Assignment ◽  
Pso Algorithm ◽  
Communication Model ◽  
Assignment Model ◽  
Cooperative Activity ◽  
Holonic Manufacturing ◽  
Theory Research ◽  
Task Assignment Problem

Manufacturing system is a typical complex system, while task assignment problem is an important topic in manufacturing system. It is one of the most difficult problems in the theory research for manufacturing system. In this paper, task assignment model in manufacturing system was modeled with the concept of Holonic Manufacturing System including basic system model, communication model, represent model and optimization model. Task assignment model based on operation cost and lead time is applied to cooperative activity among orders in a Holonic community. A hybrid PSO algorithm was utilized to the combination of the task assignment problem. Simulation result shows that the model and the algorithm are effective to the problem.

Lörres, Möppes, and the Swiss. (Re)Discovering regional patterns in anonymous social media data

2019 ◽  
Vol 7 (2) ◽  
pp. 113-134 ◽  
Author(s):  
Christoph Purschke ◽  
Dirk Hovy
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
Language Use ◽  
Representation Learning ◽  
Regional Patterns ◽  
Linguistic Resources ◽  
Large Scale Data ◽  
German Speaking ◽  
Data Collections ◽  
Media Data

AbstractWe study regional similarities and differences in language use on an anonymous mobile chat application in the German-speaking area. We use a neural network on 2.3 million online conversations to automatically learn representations of words and cities. These linguistic-use-based representations capture regional distinctions in a high-dimensional vector space that can be clustered and visualized to discover patterns in the data. We find that the resulting regional patterns are closely linked to the traditional division of German dialects, even though most of the conversations are written in standard German. The resulting maps correspond to traditional dialect divisions and language-external spatial structures, with a few notable exceptions that can be explained through external factors.Our method also facilitates two qualitative analyses, allowing us to discover geographically-pertinent words for various regional levels, as well as creating regional group-specific style profiles based on various linguistic resources. The results of our study strongly suggest the existence of region-specific patterns of language use (“digital regiolects”) representing distinctive strategies of linguistic stylization in relation to linguistic resources and topics. As a methodological contribution, we show how linguistic theory can drive the application and direction of neural network-based representation learning, and how their judicious application provides the basis for qualitative analysis of large-scale data collections.

Sign in / Sign up

Export Citation Format

Share Document