CoNet: Collaborative Cross Networks for Cross-Domain Recommendation

By Guangneng Hu, Yu Zhang, Qiang Yang. 2018

492 citations recorded by the source corpus.

The cross-domain recommendation technique is an effective way of alleviating the data sparse issue in recommender systems by leveraging the knowledge from relevant domains. Transfer learning is a class of algorithms underlying these techniques. In this paper, we propose a novel transfer learning approach for cross-domain recommendation by using neural networks as the base model. In contrast to the matrix factorization based cross-domain techniques, our method is deep transfer learning, which can learn complex user-item interaction relationships. We assume that hidden layers in two base networks are connected by cross mappings, leading to the collaborative cross networks (CoNet). CoNet enables dual knowledge transfer across domains by introducing cross connections from one base network to another and vice versa. CoNet is achieved in multi-layer feedforward networks by adding dual connections and joint loss functions, which can be trained efficiently by back-propagation. The proposed model is thoroughly evaluated on two large real-world datasets. It outperforms baselines by relative improvements of 7.84% in NDCG. We demonstrate the necessity of adaptively selecting representations to transfer. Our model can reduce tens of thousands training examples comparing with non-transfer methods and still has the competitive performance with them.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Wayne Xin Zhao
2. Xiangnan He
3. Ji-rong Wen
4. Qiang Yang
5. Yu Zhang
6. Yupeng Hou
7. Chuan Shi
8. Yaochu Jin

In Computer Vision and Pattern Recognition

1. Qiang Yang
2. Wayne Xin Zhao
3. Chuan Shi
4. Ji-rong Wen
5. Jie Lu
6. Yu Zhang
7. Yaochu Jin
8. Qian Zhang

In Information Systems

1. Wayne Xin Zhao
2. Xiangnan He
3. Ji-rong Wen
4. Chuan Shi
5. Yupeng Hou
6. Qiang Yang
7. Jie Lu
8. Fajie Yuan

Citations in the corpus

• Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation (2020, background): “es a small fraction of injected parameters, but obtains comparable or better results than fine-tuning all parameters, and performs notably better than fine-tuning only the classification layer. CoNet [18] is another cross-domain recommendation model using neural networks as the base model. To enable”
• Transfer Meets Hybrid: A Synthetic Approach for Cross-Domain Collaborative Filtering with Text (2019, methodology): “this is not easily achieved by the existing cross-domain recommendation techniques like the multitask models such as collective matrix factorization [45] and collaborative cross networks [21] (a variant of cross-stitch networks [34]) which have multi-objective optimization.”
• DDTCDR: Deep Dual Transfer Cross Domain Recommendation (2019, methodology): “• CoNet[6] Collaborative Cross Networks (CoNet) enables • NCF[5] Neural Collaborative Filtering (NCF) is a neural • CMF[30] Collective Matrix Factorization (CMF) simultaneously Furthermore, we select hyperparamter α for our study as 0.03 using”
• Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation (2020, methodology): “Additionally, some transfer learning-based methods use features from a source domain to apply to the target domain [12, 13], with the assumption that a source domain is available and users or items can be aligned in both domains.”
• Text Is All You Need: Learning Language Representations for Sequential Recommendation (2023, unknown): “Previous methods for knowledge transfer mainly rely on shared information between the source and target domains including common users [13, 31, 32, 35], items [26, 39] or attributes [29].”
• One Person, One Model, One World: Learning Continual User Representation without Forgetting (2020, unknown): “Multi-task learning (MTL) [13].”
• Towards Universal Sequence Representation Learning for Recommender Systems (2022, background): “Most works rely on explicit overlapping data for conducting the transfer across domains, such as common users [8] or items [20, 38], social networks [14] and attributes [25].”
• Artificial intelligence in recommender systems (2020, methodology): “Hu et al. also propose a cross-domain recommendation method by sharing the hidden layers between two domains [126].”
• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, background): “As an increasing number of users interact with multimodal information across multiple domains, cross-domain recommendation (CDR) has been demonstrated to be a promising method to alleviate cold start and data sparsity problems [50, 52, 70, 79, 124, 132, 238], as illustrated in Figure 7.”