Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention

By Jingyuan Chen, Hanwang Zhang, Xiangnan He, Liqiang Nie, Wei David Liu, Tat-seng Chua. 2017

947 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

In Information Systems

Citations in the corpus

RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems (2018, background): “8] and machine translation [1], which aims to learn where to find the most relevant part of the input automatically as it is performing the task. The idea was soon transplanted to recommender systems [4, 22, 33, 36, 47]. For example, DADM [4] considers factors of specialty and date when assigning at”
Disentangled Graph Collaborative Filtering (2020, background): “that, later studies like SVD++ [19], FISM [16], NAIS [11], and ACF [3] view personal history of a user as her features, and integrate embeddings of historical items via the average [16, 19] or attention network [3, 11] as user embeddings, showing promise in representation learning.”
Cross-domain Recommendation Without Sharing User-relevant Data (2019, positive): “…we apply a non-uniform coefficient when fusing the transferred item embeddings: To model the various item importance in a user-sensitive fashion, here we introduce attention mechanism, which has achieved great success in recommendation tasks [3, 13, 40] and natural language processing [20, 37].”
Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems (2020, background): “Recommender systems are emerging as an important means of facilitating users’ information seeking [6, 17, 20, 30].”
Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks (2018, methodology): “More recently, deep learning techniques have been utilized to enhance the modeling of context information, including multi-granularity attention [2], RNN with rich features [23], RNN with video semantic embedding [7] and RNN with adaptive context-specific transition matrices [20].”
Quantifying and Alleviating the Language Prior Problem in Visual Question Answering (2019, background): “For instance, Chen et al. [7] proposed a two-level attention mechanism to fuse the features from component-level and item-level for multimedia recommendation.”
Recommendation system based on deep learning methods: a systematic review and new directions (2019, background): “The main purpose of the attention technique is to provide a solution by allowing the network to better memorize inputs (Chen et al. 2017).”
NAIS: Neural Attentive Item Similarity Model for Recommendation (2018, methodology): “Note that setting β to 1 means using softmax to normalize the attention weights, a standard setting for neural attention networks [19], [15], [16].”
TEM: Tree-enhanced Embedding Model for Explainable Recommendation (2018, methodology): “Note that optimizing other objective functions are also technically viable, such as the pointwise regression loss [20, 41, 42] and ranking loss [9, 33, 44].”
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation (2020, methodology): “e importance of the k-th layer embedding in constituting the final embedding. It can be treated as a hyperparameter to be tuned manually, or as a model parameter (e.g., output of an attention network [3]) to be optimized automatically. In our experiments, we find that settingαk uniformly as 1/(K + 1”
Video Question Answering via Gradually Refined Attention over Appearance and Motion (2017, background): “Recent works [4, 11] show that the activations in the deeper layer of CNN can generalize well to other tasks, which means the activations can represent the semantics of the image.”
Outer Product-based Neural Collaborative Filtering (2018, methodology): “Moreover, we will extend ONCF to content-based recommendation scenarios [Chen et al., 2017; Yu et al., 2018], where the item features have richer semantics than just an ID.”
KGAT: Knowledge Graph Attention Network for Recommendation (2019, background): “ and recursively performs such embedding propagation to capture high-order connectivities in a linear time complexity; and 2) attention-based aggregation, which employs the neural attention mechanism [6, 27] to learn the weight of each neighbor during a propagation, such that the attention weights o”