Deep Coevolutionary Network: Embedding User and Item Features for Recommendation

Abstract

Recommender systems often use latent features to explain the behaviors of users and capture the properties of items. As users interact with different items over time, user and item features can influence each other, evolve and co-evolve over time. The compatibility of user and item's feature further influence the future interaction between users and items. Recently, point process based models have been proposed in the literature aiming to capture the temporally evolving nature of these latent features. However, these models often make strong parametric assumptions about the evolution process of the user and item latent features, which may not reflect the reality, and has limited power in expressing the complex and nonlinear dynamics underlying these processes. To address these limitations, we propose a novel deep coevolutionary network model (DeepCoevolve), for learning user and item features based on their interaction graph. DeepCoevolve use recurrent neural network (RNN) over evolving networks to define the intensity function in point processes, which allows the model to capture complex mutual influence between users and items, and the feature evolution over time. We also develop an efficient procedure for training the model parameters, and show that the learned models lead to significant improvements in recommendation and activity prediction compared to previous state-of-the-arts parametric models.

Recsys Workshop on Deep Learning for Recommendation Systems (DLRS '16)

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• On Tensors, Sparsity, and Nonnegative Factorizations
• Dynamic Poisson Factorization
• Improved Recurrent Neural Networks for Session-based Recommendations

Cited by in corpus (23)

• Graph Embedding Techniques, Applications, and Performance: A Survey
• Deep Learning based Recommender System: A Survey and New Perspectives
• DynGEM: Deep Embedding Method for Dynamic Graphs
• Keyword Transformer: A Self-Attention Model for Keyword Spotting
• Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs
• Representation Learning for Dynamic Graphs: A Survey
• TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
• Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
• Transition Propagation Graph Neural Networks for Temporal Networks
• Learning Dynamic Embeddings from Temporal Interactions
• Dynamic Hawkes Processes for Discovering Time-evolving Communities' States behind Diffusion Processes
• A Stochastic Differential Equation Framework for Guiding Online User Activities in Closed Loop
• Variational Policy for Guiding Point Processes
• CPMR: Context-Aware Incremental Sequential Recommendation with Pseudo-Multi-Task Learning
• Deep Structural Point Process for Learning Temporal Interaction Networks
• An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation
• ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding
• Dynamic Sequential Graph Learning for Click-Through Rate Prediction
• Dynamic Graph Collaborative Filtering
• Compositional Embeddings for Multi-Label One-Shot Learning
• Sequential Modelling with Applications to Music Recommendation, Fact-Checking, and Speed Reading
• Dynamic Customer Embeddings for Financial Service Applications
• Representation Learning for Efficient and Effective Similarity Search and Recommendation