Enhancing Music Features by Knowledge Transfer from User-item Log Data

03/07/2019
by   Donmoon Lee, et al.
0

In this paper, we propose a novel method that exploits music listening log data for general-purpose music feature extraction. Despite the wealth of information available in the log data of user-item interactions, it has been mostly used for collaborative filtering to find similar items or users and was not fully investigated for content-based music applications. We resolve this problem by extending intra-domain knowledge distillation to cross-domain: i.e., by transferring knowledge obtained from the user-item domain to the music content domain. The proposed system first trains the model that estimates log information from the audio contents; then it uses the model to improve other task-specific models. The experiments on various music classification and regression tasks show that the proposed method successfully improves the performances of the task-specific models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/18/2018

Deep Content-User Embedding Model for Music Recommendation

Recently deep learning based recommendation systems have been actively e...
research
11/05/2018

Deriving item features relevance from collaborative domain knowledge

An Item based recommender system works by computing a similarity between...
research
12/03/2019

Music Style Classification with Compared Methods in XGB and BPNN

Scientists have used many different classification methods to solve the ...
research
09/18/2023

Positive and Risky Message Assessment for Music Products

In this work, we propose a novel research problem: assessing positive an...
research
08/28/2018

Superhighway: Bypass Data Sparsity in Cross-Domain CF

Cross-domain collaborative filtering (CF) aims to alleviate data sparsit...
research
05/24/2018

A Hybrid Approach to Music Playlist Continuation Based on Playlist-Song Membership

Automated music playlist continuation is a common task of music recommen...
research
08/25/2022

Dynamic collaborative filtering Thompson Sampling for cross-domain advertisements recommendation

Recently online advertisers utilize Recommender systems (RSs) for displa...

Please sign up or login with your details

Forgot password? Click here to reset