Neural Collaborative Filtering
By Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, Tat-seng Chua. 2017
7,164 citations recorded by the source corpus.
In recent years, deep neural networks have yielded immense success on speech recognition, computer vision and natural language processing. However, the exploration of deep neural networks on recommender systems has received relatively less scrutiny. In this work, we strive to develop techniques based on neural networks to tackle the key problem in recommendation --- collaborative filtering --- on the basis of implicit feedback. Although some recent work has employed deep learning for recommendation, they primarily used it to model auxiliary information, such as textual descriptions of items and acoustic features of musics. When it comes to model the key factor in collaborative filtering --- the interaction between user and item features, they still resorted to matrix factorization and applied an inner product on the latent features of users and items. By replacing the inner product with a neural architecture that can learn an arbitrary function from data, we present a general framework named NCF, short for Neural network-based Collaborative Filtering. NCF is generic and can express and generalize matrix factorization under its framework. To supercharge NCF modelling with non-linearities, we propose to leverage a multi-layer perceptron to learn the user-item interaction function. Extensive experiments on two real-world datasets show significant improvements of our proposed NCF framework over the state-of-the-art methods. Empirical evidence shows that using deeper layers of neural networks offers better recommendation performance.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems, Representation & Self-Supervised Learning, Recommender Systems
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Xiangnan He
- Yoshua Bengio
- Mohit Bansal
- Tat-seng Chua
- Quoc V. Le
- Jianfeng Gao
- Percy Liang
- Kyunghyun Cho
In Computer Vision and Pattern Recognition
- Dacheng Tao
- Luc Van Gool
- Yi Yang
- Trevor Darrell
- Xiaogang Wang
- Ming-Hsuan Yang
- Cordelia Schmid
- Jitendra Malik
In Information Systems
In Representation & Self-Supervised Learning
- Xiangnan He
- Tat-seng Chua
- Yoshua Bengio
- Philip S. Yu
- Zhiyuan Liu
- Xiang Wang
- Yongfeng Zhang
- Trevor Darrell
In Recommender Systems
Citations in the corpus
- Variational Autoencoders for Collaborative Filtering (2018, methodology): “Previous collaborative filtering models with neural networks [14, 51] are trained with stochastic gradient descent where in each step a single (user, item) entry from the click matrix is randomly sampled to perform a gradient update.”
- Knowledge Graph Convolutional Networks for Recommender Systems (2019, methodology): “A traditional recommendation technique is collaborative filtering (CF), which assigns users and items ID-based representation vectors, then models their interactions by specific operation such as inner product [16] or neural networks [8].”
- DKN: Deep Knowledge-Aware Network for News Recommendation (2018, methodology): “In addition to the aforementioned DSSM [16], DeepWide [6], DeepFM [13], YouTubeNet [8] and DMF [50], other popular deep-learning-based recommender systems include Collaborative Deep Learning [44], SHINE [45], Multi-view Deep Learning [11], and Neural Collaborative Filtering [14].”
- Natural Compression for Distributed Deep Learning (2019, methodology): “We also train Neural Collaborative Filtering (NCF) (He et al., 2017) on MovieLens-20M Dataset using Cnat and compare its convergence to no compression.”
- Poisoning Attacks to Graph-Based Recommender Systems (2018, background): “hergraph-basedrecommender systems (e.g., graph convolutional neural network based recommender systems [36]), 3) designing optimized poisoning a−acks to neural network based recommender systems (e.g., [14]), and 4) designing defenses against poisoning a−acks. ACKNOWLEDGEMENTS We thank the anonymous r”
- Explainable Recommendation: A Survey and New Perspectives (2018, methodology): “[1999] noted that recommender system would be used to explain to a user what type of thing a product is, such as “this product you are looking at is similar to these other products that you have liked in the past”, which is the fundamental idea of item-based collaborative filtering; Herlocker et al.”
- Differentiable Neural Input Search for Recommender Systems (2020, methodology): “We employ various latent factor models: MF, MLP [19] and NeuMF [19] for the CF task, and FM [36], Wide&Deep [6], DeepFM [16] for the CTR prediction, where the configuration of latent factor models are the same over different methods.”
- AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations (2020, background): “He et al.[9] firstly proposed Neural Collaborative Filtering (NCF) which utilizes a dual neural network to represent a two-way interaction between user preferences and items features.”
- IIRC: Incremental Implicitly-Refined Classification (2020, background): “Deep learning algorithms have led to transformational breakthroughs in computer vision [12, 17], natural language processing [19, 50], speech processing [3, 5], reinforcement learning [36, 44], robotics [16, 1], recommender systems [11, 18], etc.”
- Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks (2017, background): “Recent works applying deep learning to recommender systems used networks with fully connected or auto-encoder architectures [44, 35, 14].”
- Neural Input Search for Large Scale Recommendation Models (2019, methodology): “In our experiments, we use the Neural Collaborative Filtering (NCF) model [10] on both of the two datasets, since it has been widely applied and”
- MLPerf Training Benchmark (2019, background): “Compared with Mask R-CNN (Huang et al., 2016) and other two-stage solutions, SSD trades speed for accuracy.”
- Information Leakage in Embedding Models (2020, neutral): “eled data is typically expensive to collect. Embeddings have also been successfully applied to other data domains including social networks [21], source code [2], YouTube watches [11], movie feedback [25], locations [12], etc. In some sense, their widespread use should not be surprising—embedding mo”
- Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System (2020, methodology): “We leave out the comparison with other collaborative filtering models, such as NeuMF [19] and NGCF [43], because LightGCN [17] is the stateof-the-art collaborative filtering method at present.”
- Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue (2019, background): “Traditional recommendation systems factorize users’ historical data (i.e., ratings on movies) to extract common preference patterns (Koren et al., 2009; He et al., 2017b).”
- Federated Meta-Learning for Recommendation (2018, background): “Deep learning for recommender systems has been studied in the literature, from the perspective of pure deep neural networks (Cheng et al., 2016; Wang et al., 2017) or combination with other methods (He et al., 2017; Guo et al., 2017).”
- Sequential Recommendation with Graph Neural Networks (2021, methodology): “• NCF [9]: This method combines matrix factorization and multilayer perceptrons to predict user interactions, and it is the stateof-the-art general recommender.”
- Latent Cross: Making Use of Context in Recurrent Recommender Systems (2018, methodology): “Cross RNN [22, 34] [29, 32, 48] [17, 37, 46] [21, 43] [11] [20] [19, 33] [41] [49]”
- Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding (2018, background): “As stated in [7], such pre-training is critical to model performance”