Page 174 - The-5th-MCAIT2021-eProceeding

With the advancements in technologies, newer methods like latent factors, MF, and DL have enhanced the
overall recommendation accuracy. The problem with these models lies in its transparency and explainability.
The other known issues associated with these algorithms are cold-start and data sparsity. Various state-of-the-
art technology advancements have been presented in the last few years. The KG can address cold-start, data
sparsity, and explainability issues associated with the previous methods. RL may assist in identifying the right
path over the KG for providing better recommendations to the end-user. Language models may assist in building
a better contextual KG to enhance the overall accuracy of the user recommendations.
To conclude, these niche technologies have a great scope and will form a base for future research in the
explainable recommendation area. The research in KG and RL are still in the nascent stages. LM seem to have
a great scope in the recommendation engine and possess a great interest in the research community.

Acknowledgements

This work is supported by the UKM through the Prime Impact Fund under Grant DIP-2020-017.

References

Ai Q, et al. 2018. “Learning Heterogeneous Knowledge Base Embeddings” In: Algorithms, v:11, p:137 (link).
Andriy Mnih, et al. 2008. “Probabilistic matrix factorization”. In: NIPS ACM. 1257–1264.
Balabanovic, et al. 1997. “Fab: content-based, collaborative recommendation”. In: ACM. 40(3): 66–72.
Bordes Antoine, et al. 2013. “Translating embeddings for multi-relational data”. In NIPS 2787–2795.
Chopra R., et al. 2020 “End-to-End Reinforcement Learning for Self-driving Car”. In: ACIE vol 1082 (link)
D. Cosley, et al., 2003 “Is seeing believing? How recommender system interfaces”. In: SIGCHI, 585–592.
Daniel D Lee, et al. 2001. “Algorithms for non-negative matrix factorization”. In: NIPS ACM 556–562.
David Silver, et al. 2016. “Mastering the game of Go with deep neural networks”. In: Nature 529, 484-489.
Ekstrand, et al. 2011. “Collaborative filtering recommender systems”. ACM 4(2): 81–173.
Fei Sun, et al. 2019. “BERT4Rec: Sequential Recommendation with BERT”. In 28 ACM 11 pages.
Ferwerda, B., et al. 2012. “Explaining Content-Based Recommendations”. regular paper.
Grover Aditya, et al. 2016. “node2vec: Scalable feature learning for networks”. In 22 ACM, 855–864.
Herlocker, J. L., et al., 2000 “Explaining collaborative filtering recommendations”. In: 2000 ACM. 241–250.
Herlocker, J. L., et al., 2000a. “Understanding and improving auto CF systems”. University of Minnesota.
J Ben Schafer, et al., 1999 “Recommender systems in e-commerce”. In: EC’99 1st ACM. Pp 158-166 (link).
Jyotirmoy Gope, et al. 2017. “A survey on solving cold start problem in RS”. In: ICCCA.(link)
Koren, Y., et al. 2009. “Matrix factorization techniques for recommender systems”. In: Computer 42-8 30-37.
Resnick, P., et al. 1994. “GroupLens: an open architecture for collaborative filtering”. In: ACM. 175–186.
Ricci, et al., 2011 “Introduction to recommender systems handbook”. In: RS handbook. Springer. 1–35.
Sarwar, B., et al. 2001. “Item-based collaborative filtering recommendation”. In: 10th ACM. 285–295.
Shaoxiong Ji, et al. 2021. “A Survey on Knowledge Graphs: Representation,” In: IEEE PP 99 (link)
Wu L., et al. 2019. “A context-aware user-item representation learning”. ACM (TOIS). 37(2): 22.
Xian Y., Z. Fu, et al. 2019. “Reinforcement Knowledge Graph Reasoning for Explainable”. In: 42 ACM.
Xiangnan He, et al. 2017. Neural Collaborative Filtering. In WWW’17. Pp 173–182.
Zhang Fuzheng, et al. 2016 “Collaborative knowledge base embedding for RS”. In 22 ACM, 353–362.
Zhang Y., et al., 2018. “Explainable Recommendation: A Survey and New Perspectives”In:arXiv:1804.11192
Zhang Y., et al., 2014. “Explicit factor models for explainable recommendation”. In: 37th ACM. 83–92.

E- Proceedings of The 5th International Multi-Conference on Artificial Intelligence Technology (MCAIT 2021) [161]
Artificial Intelligence in the 4th Industrial Revolution