The Experts below are selected from a list of 134367 Experts worldwide ranked by ideXlab platform

Meng Wang - One of the best experts on this subject based on the ideXlab platform.

  • a neural influence diffusion model for Social recommendation
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019
    Co-Authors: Peijie Sun, Richang Hong, Xiting Wang, Meng Wang
    Abstract:

    Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering (CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online Social networks, Social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a Social Platform, her potential embedding is influenced by her trusted users, with these trusted users are influenced by the trusted users' Social connections. As Social influence recursively propagates and diffuses in the Social network, each user's interests change in the recursive process. Nevertheless, the current Social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global Social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive Social diffusion process for Social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the Social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the Social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines for top-10 recommendation on the two datasets.

  • a neural influence diffusion model for Social recommendation
    arXiv: Information Retrieval, 2019
    Co-Authors: Peijie Sun, Richang Hong, Xiting Wang, Meng Wang
    Abstract:

    Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering(CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online Social networks, Social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a Social Platform, her potential embedding is influenced by her trusted users. As Social influence recursively propagates and diffuses in the Social network, each user's interests change in the recursive process. Nevertheless, the current Social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global Social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive Social diffusion process for Social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the Social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the Social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines.

Peijie Sun - One of the best experts on this subject based on the ideXlab platform.

  • a neural influence diffusion model for Social recommendation
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019
    Co-Authors: Peijie Sun, Richang Hong, Xiting Wang, Meng Wang
    Abstract:

    Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering (CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online Social networks, Social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a Social Platform, her potential embedding is influenced by her trusted users, with these trusted users are influenced by the trusted users' Social connections. As Social influence recursively propagates and diffuses in the Social network, each user's interests change in the recursive process. Nevertheless, the current Social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global Social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive Social diffusion process for Social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the Social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the Social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines for top-10 recommendation on the two datasets.

  • a neural influence diffusion model for Social recommendation
    arXiv: Information Retrieval, 2019
    Co-Authors: Peijie Sun, Richang Hong, Xiting Wang, Meng Wang
    Abstract:

    Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering(CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online Social networks, Social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a Social Platform, her potential embedding is influenced by her trusted users. As Social influence recursively propagates and diffuses in the Social network, each user's interests change in the recursive process. Nevertheless, the current Social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global Social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive Social diffusion process for Social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the Social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the Social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines.

Richang Hong - One of the best experts on this subject based on the ideXlab platform.

  • a neural influence diffusion model for Social recommendation
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019
    Co-Authors: Peijie Sun, Richang Hong, Xiting Wang, Meng Wang
    Abstract:

    Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering (CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online Social networks, Social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a Social Platform, her potential embedding is influenced by her trusted users, with these trusted users are influenced by the trusted users' Social connections. As Social influence recursively propagates and diffuses in the Social network, each user's interests change in the recursive process. Nevertheless, the current Social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global Social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive Social diffusion process for Social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the Social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the Social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines for top-10 recommendation on the two datasets.

  • a neural influence diffusion model for Social recommendation
    arXiv: Information Retrieval, 2019
    Co-Authors: Peijie Sun, Richang Hong, Xiting Wang, Meng Wang
    Abstract:

    Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering(CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online Social networks, Social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a Social Platform, her potential embedding is influenced by her trusted users. As Social influence recursively propagates and diffuses in the Social network, each user's interests change in the recursive process. Nevertheless, the current Social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global Social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive Social diffusion process for Social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the Social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the Social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines.

Xiting Wang - One of the best experts on this subject based on the ideXlab platform.

  • a neural influence diffusion model for Social recommendation
    International ACM SIGIR Conference on Research and Development in Information Retrieval, 2019
    Co-Authors: Peijie Sun, Richang Hong, Xiting Wang, Meng Wang
    Abstract:

    Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering (CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online Social networks, Social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a Social Platform, her potential embedding is influenced by her trusted users, with these trusted users are influenced by the trusted users' Social connections. As Social influence recursively propagates and diffuses in the Social network, each user's interests change in the recursive process. Nevertheless, the current Social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global Social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive Social diffusion process for Social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the Social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the Social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines for top-10 recommendation on the two datasets.

  • a neural influence diffusion model for Social recommendation
    arXiv: Information Retrieval, 2019
    Co-Authors: Peijie Sun, Richang Hong, Xiting Wang, Meng Wang
    Abstract:

    Precise user and item embedding learning is the key to building a successful recommender system. Traditionally, Collaborative Filtering(CF) provides a way to learn user and item embeddings from the user-item interaction history. However, the performance is limited due to the sparseness of user behavior data. With the emergence of online Social networks, Social recommender systems have been proposed to utilize each user's local neighbors' preferences to alleviate the data sparsity for better user embedding modeling. We argue that, for each user of a Social Platform, her potential embedding is influenced by her trusted users. As Social influence recursively propagates and diffuses in the Social network, each user's interests change in the recursive process. Nevertheless, the current Social recommendation models simply developed static models by leveraging the local neighbors of each user without simulating the recursive diffusion in the global Social network, leading to suboptimal recommendation performance. In this paper, we propose a deep influence propagation model to stimulate how users are influenced by the recursive Social diffusion process for Social recommendation. For each user, the diffusion process starts with an initial embedding that fuses the related features and a free user latent vector that captures the latent behavior preference. The key idea of our proposed model is that we design a layer-wise influence propagation structure to model how users' latent embeddings evolve as the Social diffusion process continues. We further show that our proposed model is general and could be applied when the user~(item) attributes or the Social network structure is not available. Finally, extensive experimental results on two real-world datasets clearly show the effectiveness of our proposed model, with more than 13% performance improvements over the best baselines.

Felix B Tan - One of the best experts on this subject based on the ideXlab platform.

  • what influences employees to use enterprise Social networks a socio technical perspective
    Pacific Asia Conference on Information Systems, 2015
    Co-Authors: Christie Peiyee Chin, Nina Evans, Kimkwang Raymond Choo, Felix B Tan
    Abstract:

    The adoption of enterprise Social network (ESN) for greater employee engagement and knowledge sharing practices within organisations is proliferating. However, ESN investments have thus far not resulted in expected gains in organisational benefits due to underutilisation by employees. Limited understanding of the implications of ESN use leads to a paucity of recommendations for effective use within an organisation. This research-in-progress paper seeks to determine the factors influencing the use of ESN among employees in a large Australian utility organisation, with the aim of contributing to a practical understanding of the key success factors of the use of this new workplace Social Platform. Our preliminary findings indicated that the employees’ ESN behaviour tends to be influenced by socio-technical factors, including technological (i.e. Platform and content quality), organisational (i.e. top management support and ESN facilitating conditions), Social (i.e. critical mass and communication climate), individual (i.e. perceived benefits, knowledge self-efficacy and time commitment) and task (i.e. task characteristics) factors. This paper concludes that a successful implementation of ESN in an organisation involves the nexus between these five factors and provides several recommendations about how ESN use can be enhanced.