Recurrent knowledge graph embedding for effective recommendation

Sun, Zhu; Yang, Jie; Zhang, Jie; Bozzon, Alessandro; Huang, Long-Kai; Xu, Changxin

doi:10.1145/3240323.3240361

Cited by 310 publications

(135 citation statements)

References 30 publications

(32 reference statements)

Supporting

Mentioning

133

Contrasting

Unclassified

Order By: Relevance

“…The fraction of papers that were reproducible according to our relatively strict criteria per conference series are shown in Table 1. Non-reproducible: KDD: [43], RecSys: [41], [6], [38], [44], [21], [45], SIGIR: [32], [7], WWW: [42], [11] Overall, we could reproduce only about one third of the works, which confirms previous discussions about limited reproducibility, see, e.g., [3]. The sample size is too small to make reliable conclusions regarding the difference between conference series.…”

Section: Research Methods 21 Collecting Reproducible Papersmentioning

confidence: 99%

Are we really making much progress? A worrying analysis of recent neural recommendation approaches

Dacrema

Cremonesi

Jannach

2019

Proceedings of the 13th ACM Conference on Recommender Systems

429

166

View full text Add to dashboard Cite

Deep learning techniques have become the method of choice for researchers working on algorithmic aspects of recommender systems. With the strongly increased interest in machine learning in general, it has, as a result, become difficult to keep track of what represents the state-of-the-art at the moment, e.g., for top-n recommendation tasks. At the same time, several recent publications point out problems in today's research practice in applied machine learning, e.g., in terms of the reproducibility of the results or the choice of the baselines when proposing new models.In this work, we report the results of a systematic analysis of algorithmic proposals for top-n recommendation tasks. Specifically, we considered 18 algorithms that were presented at top-level research conferences in the last years. Only 7 of them could be reproduced with reasonable effort. For these methods, it however turned out that 6 of them can often be outperformed with comparably simple heuristic methods, e.g., based on nearest-neighbor or graph-based techniques. The remaining one clearly outperformed the baselines but did not consistently outperform a well-tuned nonneural linear ranking method. Overall, our work sheds light on a number of potential problems in today's machine learning scholarship and calls for improved scientific practices in this area.

show abstract

Section: Research Methods 21 Collecting Reproducible Papersmentioning

confidence: 99%

Are we really making much progress? A worrying analysis of recent neural recommendation approaches

Dacrema

Cremonesi

Jannach

2019

Proceedings of the 13th ACM Conference on Recommender Systems

429

166

View full text Add to dashboard Cite

show abstract

“…A visible path often justifies recommendation. Sun et al presented a method named recurrent knowledge graph embedding (RKGE) [53], which adopts a recurrent network architecture to automatically learn the semantic representation of the path between entities. It provides a meaningful interpretation of the recommendation results.…”

Section: ) Recommendation Systemmentioning

confidence: 99%

Review Study of Interpretation Methods for Future Interpretable Machine Learning

Zhou

2020

IEEE Access

View full text Add to dashboard Cite

In recent years, black-box models have developed rapidly because of their high accuracy. Balancing the interpretability and accuracy is increasingly important. The lack of interpretability severely limits the application of the model in academia and industry. Despite the various interpretable machine learning methods, the perspective and meaning of the interpretation are also different. We provide a review of the current interpretable methods and divide them based on the model being applied. We divide them into two categories: interpretable methods with the self-explanatory model and interpretable methods with external co-explanation. And the interpretable methods with external co-explanation are further divided into subbranch methods based on instances, SHAP, knowledge graph, deep learning, and clustering model. The classification aims to help us understand the model characteristics applied in the interpretable method better. This survey makes the researcher find a suitable model to solve interpretability problems more easily. And the comparison experiments contribute to discovering complementary features from different methods. At the same time, we explore the future challenges and trends of interpretable machine learning to promote the development of interpretable machine learning. INDEX TERMS Deep learning, interpretable machine learning, interpretable methods with the selfexplanatory model, interpretable methods with external co-explanation, influential instance, knowledge graph.

show abstract

“…However, constructing paths between users and items isn't a scalable approach when the number of users and items are very large. Under such situation, sampling [2,37] and pruning [34,40] must be involved. However, RCF is free from this problem.…”

Section: Knowledge Graph Enhanced Recommendationmentioning

confidence: 99%

Relational Collaborative Filtering

Xin

Zhang

et al. 2019

Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

147

View full text Add to dashboard Cite

Existing item-based collaborative filtering (ICF) methods leverage only the relation of collaborative similarity -i.e., the item similarity evidenced by user interactions like ratings and purchases. Nevertheless, there exist multiple relations between items in real-world scenarios, e.g., two movies share the same director, two products complement with each other, etc. Distinct from the collaborative similarity that implies co-interact patterns from the user's perspective, these relations reveal fine-grained knowledge on items from different perspectives of meta-data, functionality, etc. However, how to incorporate multiple item relations is less explored in recommendation research.In this work, we propose Relational Collaborative Filtering (RCF) to exploit multiple item relations in recommender systems. We find that both the relation type (e.g., shared director) and the relation value (e.g., Steven Spielberg) are crucial in inferring user preference. To this end, we develop a two-level hierarchical attention mechanism to model user preference -the first-level attention discriminates which types of relations are more important, and the second-level attention considers the specific relation values to estimate the contribution of a historical item. To make the item embeddings be reflective of the relational structure between items, we further formulate a task to preserve the item relations, and jointly train it with user preference modeling. Empirical results on two real datasets demonstrate the strong performance of RCF 1 . Furthermore, we also conduct qualitative analyses to show the benefits of explanations brought by RCF's modeling of multiple item relations. CCS CONCEPTS• Information systems → Recommender systems; Retrieval models and ranking; Novelty in information retrieval.

show abstract

Recurrent knowledge graph embedding for effective recommendation

Cited by 310 publications

References 30 publications

Are we really making much progress? A worrying analysis of recent neural recommendation approaches

Are we really making much progress? A worrying analysis of recent neural recommendation approaches

Review Study of Interpretation Methods for Future Interpretable Machine Learning

Relational Collaborative Filtering

Contact Info

Product

Resources

About