Personalized Music Recommendation with Triplet Network
This work aims to improve personalized music recommendations for users of online services, but it appears incremental as it applies an existing triplet network method to a specific domain.
The authors tackled the problem of music recommendation by proposing a triplet neural network to learn user-item representations and distance measures, addressing challenges like feature representation and cold start.
Since many online music services emerged in recent years so that effective music recommendation systems are desirable. Some common problems in recommendation system like feature representations, distance measure and cold start problems are also challenges for music recommendation. In this paper, I proposed a triplet neural network, exploiting both positive and negative samples to learn the representation and distance measure between users and items, to solve the recommendation task.