JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation

  title={JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation},
  author={Zhiwei Liu and Lei Zheng and Jiawei Zhang and Jiayu Han and Philip S. Yu},
  journal={2019 IEEE International Conference on Big Data (Big Data)},
Cross-domain recommendation can alleviate the data sparsity problem in recommender systems. To transfer the knowledge from one domain to another, one can either utilize the neighborhood information or learn a direct mapping function. However, all existing methods ignore the high-order connectivity information in cross-domain recommendation area and suffer from the domain-incompatibility problem. In this paper, we propose a Joint Spectral Convolutional Network (JSCN) for cross-domain… 

Pre-training Graph Neural Network for Cross Domain Recommendation

A novel Pre-training Graph Neural Network for Cross-Domain Recommendation (PCRec), which adopts the contrastive self-supervised pre-training of a graph encoder, which benefits the fine-tuning of the single domain recommender system on the target domain.

HeroGRAPH: A Heterogeneous Graph Framework for Multi-Target Cross-Domain Recommendation

Experiments on real-world datasets show that HeroGRAPH can effectively transfer information between domains and alleviate the sparsity issue and a recurrent attention to model heterogeneous neighbors for each node is proposed.

CFCR: A Convolution and Fusion Model for Cross-platform Recommendation

The proposed CFCR model utilizes Graph Convolution Networks (GCN) to extract user and item features on graphs from different platforms, and fuses cross-platform information by Multimodal AutoEncoder with common latent user features to ensure high-order connectivity information is preserved to the most extent and domain-invariant user representations are automatically obtained.

Cross-Domain Sequential Recommendation Based on Self-Attention and Transfer Learning

This paper proposes a new cross-domain sequential recommendation model (SATLR) based on self-attention and transfer learning, which make recommendations based on user preferences and sequential dependencies learn from cross- domain.

Deoscillated Adaptive Graph Collaborative Filtering

A new RS model, named as Deoscillated adaptive Graph Collaborative Filtering (DGCF), which is constituted by stacking multiple CHP layers and LA layers is proposed, and detailed analyses indicate that DGCF solves oscillation problems, adaptively learns local factors, and has layer-wise propagation patterns.

Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems

It is shown that existing neural systems initialized with LEPORID often perform on par or better than KNN, and the Dual-Loss Residual Recommendation (DLR^2) network is proposed, which substantially outperforms both traditional and state-of-the-art neural recommender systems.

BasConv: Aggregating Heterogeneous Interactions for Basket Recommendation with Graph Convolutional Neural Network

A new framework named BasConv, which is based on the graph convolutional neural network, and has three types of aggregators specifically designed forThree types of nodes, which collectively learn node embeddings from both neighborhood and high-order context.

Deoscillated Graph Collaborative Filtering

A new RS model, named as DGCF, is proposed, which models high-order CF signals adaptively to the locality of nodes and layers and introduces cross-hop propagation layers in it to break the bipartite propagating structure, thus resolving the oscillation problem.

Detecting User Community in Sparse Domain via Cross-Graph Pairwise Learning

The model, Pairwise Cross-graph Community Detection (PCCD), is proposed to cope with the sparse graph problem by involving external graph knowledge to learn user pairwise community closeness instead of detecting direct communities.

ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation

This work intends to empower the GNN model with the ability to tackle the social inconsistency problem by proposing to sample consistent neighbors by relating sampling probability with consistency scores between neighbors and employing the relation attention mechanism to assign consistent relations with high importance factors for aggregation.



CoNet: Collaborative Cross Networks for Cross-Domain Recommendation

This paper proposes a novel transfer learning approach for cross-domain recommendation by using neural networks as the base model, which can reduce tens of thousands training examples comparing with non-transfer methods and still has the competitive performance with them.

MTNet: A Neural Approach for Cross-Domain Recommendation with Unstructured Text

A novel neural model, MTNet, is proposed for cross-domain recommendation with unstructured text in an end-to-end manner and shows better performance in terms of three ranking metrics by comparing with various baselines, including single/cross domain, shallow/deep, and hybrid methods.

Cross-Domain Recommendation for Cold-Start Users via Neighborhood Based Feature Mapping

A Cross-Domain Latent Feature Mapping (CDLFM) model for cold-start users in the target domain is proposed that takes the users' similarity relationship on rating behaviors into consideration and proposes the Matrix Factorization by incorporating User Similarities (MFUS) in which three similarity measures are proposed.

A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems

This work proposes a content-based recommendation system to address both the recommendation quality and the system scalability, and proposes to use a rich feature set to represent users, according to their web browsing history and search queries, using a Deep Learning approach.

Personalized recommendation via cross-domain triadic factorization

This paper proposes a generalized Cross Domain Triadic Factorization (CDTF) model over the triadic relation user-item-domain, which can better capture the interactions between domain-specific user factors and item factors.

Joint Representation Learning for Top-N Recommendation with Heterogeneous Information Sources

This work analyzes how information propagates among different information sources in a gradient-descent learning paradigm, and proposes an extendable version of the JRL framework (eJRL), which is rigorously extendable to new information sources to avoid model re-training in practice.

Convolutional Matrix Factorization for Document Context-Aware Recommendation

A novel context-aware recommendation model that integrates convolutional neural network (CNN) into probabilistic matrix factorization (PMF) that captures contextual information of documents and further enhances the rating prediction accuracy is proposed.

Spectral collaborative filtering

Benefiting from the rich information of connectivity existing in the spectral domain, SpectralCF is capable of discovering deep connections between users and items and therefore, alleviates the cold-start problem for CF.

Joint Deep Modeling of Users and Items Using Reviews for Recommendation

A deep model to learn item properties and user behaviors jointly from review text, named Deep Cooperative Neural Networks (DeepCoNN), consists of two parallel neural networks coupled in the last layers.

Deep Cross Networks with Aesthetic Preference for Cross-domain Recommendation

A new deep Aesthetic preference Cross-Domain Network (ACDN), in which parameters characterizing personal aesthetic preferences are shared across networks to transfer knowledge between domains, is proposed, which outperforms other benchmark methods in terms of recommendation accuracy.