论文标题
行为歌曲嵌入的多目标超参数优化
Multi-objective Hyper-parameter Optimization of Behavioral Song Embeddings
论文作者
论文摘要
歌曲嵌入是大多数音乐推荐引擎的关键组成部分。在这项工作中，我们研究了基于Word2Vec的行为歌曲嵌入的高参数优化，以选择下游任务，即次生建议，错误的邻居拒绝，艺术家和流派聚类。我们提出了新的优化目标和指标，以监视超参数优化的效果。我们表明，单目标优化会对非优化指标产生副作用，并提出简单的多目标优化以减轻这些效果。我们发现，Word2Vec的次音建议质量与歌曲的流行相关，并且我们展示了歌曲嵌入优化如何平衡跨不同流行级别的性能。然后，我们对游戏预测任务显示潜在的积极下游影响。最后，我们通过测试在行业规模数据集中测试超参数优化的培训数据集量表的影响。
Song embeddings are a key component of most music recommendation engines. In this work, we study the hyper-parameter optimization of behavioral song embeddings based on Word2Vec on a selection of downstream tasks, namely next-song recommendation, false neighbor rejection, and artist and genre clustering. We present new optimization objectives and metrics to monitor the effects of hyper-parameter optimization. We show that single-objective optimization can cause side effects on the non optimized metrics and propose a simple multi-objective optimization to mitigate these effects. We find that next-song recommendation quality of Word2Vec is anti-correlated with song popularity, and we show how song embedding optimization can balance performance across different popularity levels. We then show potential positive downstream effects on the task of play prediction. Finally, we provide useful insights on the effects of training dataset scale by testing hyper-parameter optimization on an industry-scale dataset.
