Logo image
Mitigating Data Sparsity via Neuro-Symbolic Knowledge Transfer [CEUR-WS]
Conference proceeding   Open access   Peer reviewed

Mitigating Data Sparsity via Neuro-Symbolic Knowledge Transfer [CEUR-WS]

T Carraro, Alessandro Daniele, F Aiolli and L Serafini
KaRS 2023: Knowledge-aware and Conversational Recommender Systems 2023, Vol.3560, pp.69-79
CEUR Workshop Proceedings, 3560
KaRS: 2023 Knowledge-aware and Conversational Recommender Systems 2023 (Singapore, 19/09/2023–19/09/2023)
2023
Handle:
https://hdl.handle.net/10863/52178

Abstract

Knowledge transfer data sparsity logic tensor networks explicit feedback neuro-symbolic integration rating prediction Matrix factorization
Data sparsity is a well-known historical limitation of recommender systems that still impacts the performance of state-of-the-art approaches. One practical technique to mitigate this issue involves transferring information from other domains or tasks to compensate for scarcity in the target domain, where the recommendations must be performed. Following this idea, we propose a novel approach based on Neuro-Symbolic computing designed for the knowledge transfer task in recommender systems. In particular, we use a Logic Tensor Network (LTN) to train a vanilla Matrix Factorization (MF) model for rating prediction. We show how the LTN can be used to regularize the MF model using axiomatic knowledge that permits injecting pre-trained information learned by Collaborative Filtering on a different task or domain. Extensive experiments comparing our model with a baseline MF on two versions of a novel real-world dataset prove our proposal’s potential in the knowledge transfer task. In particular, our model consistently outperforms the MF, suggesting that the knowledge is effectively transferred to the target domain via logical reasoning. Moreover, an experiment that drastically decreases the density of user-item ratings shows that the benefits of the acquired knowledge increase with the sparsity of the dataset, showing the importance of exploiting knowledge from a denser source of information when training data is scarce in the target domain.
pdf
long5350.74 kBDownloadView
Open Access
url
https://ceur-ws.org/Vol-3560View
url
https://ceur-ws.org/Vol-3560/long5.pdfView

Details

Metrics

1 Record Views
Logo image