Social Influence-Based Group Representation Learning for Group Recommendation

Yin, Hongzhi; Wang, Qinyong; Zheng, Kai; Li, Zhixu; Yang, Jiali; Zhou, Xiaofang

doi:10.1109/icde.2019.00057

Cited by 160 publications

(83 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly, the compilation of all user's comments highlights a generic perception of the underlined image by the community, which likely includes a set of image descriptors and main patterns that will increase the matching with image captioning system. On the other hands, one may also mention other factors that do influence the users' textual inputs related to personal and sociological factors [32], [33]. Among these factors, which are found to impact the structure of the comment, and thereby, the overlap value, one shall mention: the user culture, the age and gender of the user, te travel experience of the user, the mood of the user while he was writing his comment, the nature of image itself weather it is know or unknown (famous status).…”

Section: Preliminary Analysis Resultsmentioning

confidence: 99%

Reconciling Image Captioning and User’s Comments for Urban Tourism

Bounab

Oussalah

Ferdenache

2020

2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA)

View full text Add to dashboard Cite

Image captioning as a process of assigning textual description to an image has gained momentum nowadays thanks to recent advances in deep learning related architectures and availability of associated tools. In the era of digital tourism, this offers a valuable framework to reconcile the widely available tourism images and user's generated content. This paper presents a novel approach to perform such reconciliation in a way to benefit tourism industry. Especially, IMGUR online image sharing services has been employed to construct a novel database, referred Tourism48, which contains gallery tourism images from 48 countries together with their associated user's comments. Google Cloud Vision API has been employed to perform image captioning of the underlined images, while similarity analysis has been employed to match user's comments to the obtained captioning results. The outcomes can trigger the development of subsequent policy research in tourism industry and behavior analysis. Besides, the Tourism48 dataset has been made available for research community. 1 Index Terms-Image captioning, social media, image description, string matching, google vision API.

show abstract

Section: Preliminary Analysis Resultsmentioning

confidence: 99%

Reconciling Image Captioning and User’s Comments for Urban Tourism

Bounab

Oussalah

Ferdenache

2020

2020 Tenth International Conference on Image Processing Theory, Tools and Applications (IPTA)

View full text Add to dashboard Cite

show abstract

“…In the SIPM procedure, inspired by the success of [2,30] in learning (user) group preference based on both user-item and group-item interaction data, we utilize the bipartite graph embedding model (BGEM) and attention mechanism to obtain each worker group's preference on different categories of tasks by simultaneously leveraging both worker-task and group-task interaction data. Note that we say a worker interacts with a task if she has performed this task.…”

Section: Framework Overviewmentioning

confidence: 99%

“…In particular, we can calculate a social network feature vector for worker w k and employ a feature selector vector to assign different weights to different structure features [30]. We normalize all the feature values into the range [0,1].…”

Section: Group Interaction Modelingmentioning

confidence: 99%

Consensus-Based Group Task Assignment with Social Impact in Spatial Crowdsourcing

Zhao

Zhou

et al. 2020

Data Sci. Eng.

Self Cite

View full text Add to dashboard Cite

With the pervasiveness of GPS-enabled smart devices and increased wireless communication technologies, spatial crowdsourcing (SC) has drawn increasing attention in assigning location-sensitive tasks to moving workers. In real-world scenarios, for the complex tasks, SC is more likely to assign each task to more than one worker, called group task assignment (GTA), for the reason that an individual worker cannot complete the task well by herself. It is a challenging issue to assign worker groups the tasks that they are interested in and willing to perform. In this paper, we propose a novel framework for group task assignment based on worker groups’ preferences, which includes two components: social impact-based preference modeling (SIPM) and preference-aware group task assignment (PGTA). SIPM employs a bipartite graph embedding model and the attention mechanism to learn the social impact-based preferences of different worker groups on different task categories. PGTA utilizes an optimal task assignment algorithm based on the tree decomposition technique to maximize the overall task assignments, in which we give higher priorities to the worker groups showing more interests in the tasks. We further optimize the original framework by proposing strategies to improve the effectiveness of group task assignment, wherein a deep learning method and the group consensus are taken into consideration. Extensive empirical studies verify that the proposed techniques and optimization strategies can settle the problem nicely.

show abstract

“…Learning continuous low-dimensional vector representations of nodes in a network has recently attracted substantial research interest. Data from networks such as E-commerce platforms, scholarly libraries, social media, medicine, service providers [2,5,24,25] etc. in its raw form is not directly applicable to emerging Machine Learning (ML) approaches, as they requires low-dimensional vector representations for computation.…”

Section: Introductionmentioning

confidence: 99%

Decentralized Embedding Framework for Large-Scale Networks

Imran

Yin

Chen

et al. 2020

Database Systems for Advanced Applications

Self Cite

View full text Add to dashboard Cite

Network embedding aims to learn vector representations of vertices, that preserve both network structures and properties. However, most existing embedding methods fail to scale to large networks. A few frameworks have been proposed by extending existing methods to cope with network embedding on large-scale networks. These frameworks update the global parameters iteratively or compress the network while learning vector representation. Such network embedding schemes inevitably lead to a high cost of either high communication overhead or sub-optimal embedding quality. In this paper, we propose a novel decentralized large-scale network embedding framework called DeLNE. As the name suggests, DeLNE divides a network into smaller partitions and learn vector representation in a distributed fashion, avoiding any unnecessary communication overhead. Our proposed framework uses Variational Graph Convolution Auto-Encoders to embed the structure and properties of each sub-network. Secondly, we propose an embedding aggregation mechanism, that captures the global properties of each node. Thirdly, we propose an alignment function, that reconciles all subnetworks embedding into the same vector space. Due to the parallel nature of DeLNE, it scales well on large clustered environments. Through extensive experimentation on realistic datasets, we show that DeLNE produces high-quality embedding and outperforms existing large-scale network embeddings frameworks, in terms of both efficiency and effectiveness.

show abstract

Social Influence-Based Group Representation Learning for Group Recommendation

Cited by 160 publications

References 28 publications

Reconciling Image Captioning and User’s Comments for Urban Tourism

Reconciling Image Captioning and User’s Comments for Urban Tourism

Consensus-Based Group Task Assignment with Social Impact in Spatial Crowdsourcing

Decentralized Embedding Framework for Large-Scale Networks

Contact Info

Product

Resources

About