Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation

Abstract

Recently, micro-video sharing platforms such as Kuaishou and Tiktok have become a major source of information for people's lives. Thanks to the large traffic volume, short video lifespan and streaming fashion of these services, it has become more and more pressing to improve the existing recommender systems to accommodate these challenges in a cost-effective way. In this paper, we propose a novel concept-aware denoising graph neural network (named Conde) for micro-video recommendation. Conde consists of a three-phase graph convolution process to derive user and micro-video representations: warm-up propagation, graph denoising and preference refinement. A heterogeneous tripartite graph is constructed by connecting user nodes with video nodes, and video nodes with associated concept nodes, extracted from captions and comments of the videos. To address the noisy information in the graph, we introduce a user-oriented graph denoising phase to extract a subgraph which can better reflect the user's preference. Despite the main focus of micro-video recommendation in this paper, we also show that our method can be generalized to other types of tasks. Therefore, we also conduct empirical studies on a well-known public E-commerce dataset. The experimental results suggest that the proposed Conde achieves significantly better recommendation performance than the existing state-of-the-art solutions. CCS CONCEPTS• Information systems → Recommender systems.

Temporal Diversity-Aware Micro-Video Recommendation with Long- and Short-Term Interests Modeling

“…In recent years, many approaches based on deep learning methods have been proposed for micro-video recommendation [2][3][4][5][6][7][8][9][10][11][12][14][15][16][17][18][19], including recurrent neural network (RNN) [4,14], self-attention mechanism [2,6,8,15], and graph convolution network (GCN) [3,9,11,12,[17][18][19]. For instance, Li et al [4] designed a temporal graph-based sequential network to capture users' positive and negative interests from multi-behaviors.…”

Human Pose Driven Object Effects Recommendation

“…Micro-video recommendation & video product recommendation With the wide spread of micro-videos and their increasing popularity, micro-video recommendation and video product recommendation have attracted numerous attention (Wei et al 2019;Liu et al 2021b;Cao et al 2020;Jiang et al 2020;Bouchacourt, Tomioka, and Nowozin 2018;Liu et al 2020;Lu et al 2021;Zhu et al 2019;Jin, Xu, and He 2019;Li et al 2019b;Chen et al 2019; Cheng et al 2016Cheng et al , 2017Zhang et al 2020a). The common idea of existing methods is to learn powerful features from images/autos/texts for accurate video-item registration (Wei et al 2019;Liu et al 2021b;Lei et al 2021;Yang, Wang, and Jiang 2020). In this work, we propose the new topic of object effects recommendation for micro-videos.…”

Research on data mining and the short video platforms users' personalized information needs

“…Data mining is an effective means to analyze and reveal the potential value information implied in data, in the current era of big data, data mining has attracted the attention of many scholars [2]. The design of personalized recommendation systems in various fields is an important direction of data mining research, such as: personalized recommendation system for literature [3], web pages [4], libraries [5], and short videos [6]. The so-called personalized recommendation is a recommendation algorithm or system based on the development and rise of the Internet to achieve the individual needs of users [7].…”

“…The so-called personalized recommendation is a recommendation algorithm or system based on the development and rise of the Internet to achieve the individual needs of users [7]. Through consulting the relevant literature, it is found that the existing short video personalized algorithm recommendation technology mainly includes three methods: the recommendation method based on user portraits, the content-based filtering method and the collaborative filtering method [6]. The recommendation method based on user portraits is mainly based on the user's basic information, such as login information, social information and interaction information with the platform.…”