Unsupervised graph-based rank aggregation for improved retrieval |
| |
| Institution: | 1. Institute of Computing, University of Campinas (UNICAMP), Campinas, Brazil;2. Department of Statistics, Applied Mathematics and Computing, São Paulo State University (UNESP), Rio Claro, Brazil;1. College of Hotel and Tourism Management, Kyung Hee University, Kyung Hee Dearo 26, Dongdeamun-Gu, Seoul 130-701, Republic of Korea;2. Faculty of Communication Sciences, USI - Università della Svizzera italiana, Switzerland;1. Department of Hotel Management, Graduate School, Kyung Hee University, Republic of Korea;2. Department of Hotel Management, College of Hotel and Tourism Management, Kyung Hee University, Republic of Korea;3. Department of Culture, Tourism & Contents, College of Hotel and Tourism Management, Kyung Hee University, 26 Kyungheedae-ro, Dongdaemun-gu, Seoul 02447, Republic of Korea;1. International Doctoral Innovation Centre, University of Nottingham, 199 Taikang East Road, 315100 Ningbo, China;2. Product Design and Manufacture, Department of Mechanical, Materials and Manufacturing Engineering, University of Nottingham, 199 Taikang East Road, 315100 Ningbo, China;3. Institute of Computing & Cyber Systems, Michigan Technological University, Houghton, MI, USA;4. Lab for Uncertainty in Data and Decision Making, School of Computer Science, University of Nottingham, Jubilee Campus, Wollaton Road, NG8 1BB Nottingham, UK;1. School of Economics and Management, Beihang University, Beijing 100191, China;2. Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University, Beijing 100191, China;3. Beijing Key Laboratory of Emergency Support Simulation Technologies for City Operations, Beihang University, Beijing 100191, China |
| |
| Abstract: | This paper presents a robust and comprehensive graph-based rank aggregation approach, used to combine results of isolated ranker models in retrieval tasks. The method follows an unsupervised scheme, which is independent of how the isolated ranks are formulated. Our approach is able to combine arbitrary models, defined in terms of different ranking criteria, such as those based on textual, image or hybrid content representations.We reformulate the ad-hoc retrieval problem as a document retrieval based on fusion graphs, which we propose as a new unified representation model capable of merging multiple ranks and expressing inter-relationships of retrieval results automatically. By doing so, we claim that the retrieval system can benefit from learning the manifold structure of datasets, thus leading to more effective results. Another contribution is that our graph-based aggregation formulation, unlike existing approaches, allows for encapsulating contextual information encoded from multiple ranks, which can be directly used for ranking, without further computations and post-processing steps over the graphs. Based on the graphs, a novel similarity retrieval score is formulated using an efficient computation of minimum common subgraphs. Finally, another benefit over existing approaches is the absence of hyperparameters.A comprehensive experimental evaluation was conducted considering diverse well-known public datasets, composed of textual, image, and multimodal documents. Performed experiments demonstrate that our method reaches top performance, yielding better effectiveness scores than state-of-the-art baseline methods and promoting large gains over the rankers being fused, thus demonstrating the successful capability of the proposal in representing queries based on a unified graph-based model of rank fusions. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
