Proceedings of the ACM Recommender Systems Challenge 2018最新文献

Towards Seed-Free Music Playlist Generation: Enhancing Collaborative Filtering with Playlist Title Information 迈向无种子音乐播放列表生成:增强与播放列表标题信息的协同过滤

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267485

Jaehun Kim, Minz Won, Cynthia C. S. Liem, A. Hanjalic

引用次数: 9

Automatic playlist continuation using a hybrid recommender system combining features from text and audio 使用混合推荐系统，结合文本和音频的功能，自动播放列表延续

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267473

Andrés Ferraro, D. Bogdanov, Jisang Yoon, Kwangseob Kim, Xavier Serra

引用次数: 15

Efficient K-NN for Playlist Continuation 播放列表延续的高效K-NN算法

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267477

Domokos M. Kelen, Dániel Berecz, Ferenc Béres, A. Benczúr

引用次数: 8

MMCF: Multimodal Collaborative Filtering for Automatic Playlist Continuation 自动播放列表延续的多模态协同过滤

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267482

Hojin Yang, Yoonki Jeong, Minjin Choi, Jongwuk Lee

{"title":"MMCF: Multimodal Collaborative Filtering for Automatic Playlist Continuation","authors":"Hojin Yang, Yoonki Jeong, Minjin Choi, Jongwuk Lee","doi":"10.1145/3267471.3267482","DOIUrl":"https://doi.org/10.1145/3267471.3267482","url":null,"abstract":"Automatic playlist continuation (APC) is a common task of music recommender systems, enabling the automatic discovery of tracks that fit into a given playlist. To recommend a coherent list of tracks to users, it is important to capture the underlying characteristics of a playlist. Unfortunately, existing recommender models suffer from several problems: (1) They tend to misinterpret tracks that appear rarely in a playlist (popularity bias) (2) they cannot extend user's playlist that consists of very few tracks (cold-start problem), and (3) they neglect the context of a playlist such as the sequence of tracks or playlist title (context-aware continuation). This year's ACM RecSys Challenge'18 aimed to find new solutions to tackle these problems. In this paper, we propose a multimodal collaborative filtering model to deal effectively with diverse data. This consists of two components: (1) an autoencoder using both the playlist and its categorical contents and (2) a character-level convolutional neural network using the playlist title only. By simultaneously analyzing the playlist and the categorical contents, our model successfully addresses the cold-start and popularity bias problems. In addition, we consider the context of a playlist by utilizing its title, thus enhancing the prediction of well-suited tracks. In the challenge, our team \"hello world!\" was ranked the 2nd place, scoring 0.224, 0.394, and 1.928 for the three evaluation metrics, respectively. Our implementation code is publicly available at https://github.com/hojinYang/spotify_recSys_challenge_2018.","PeriodicalId":430663,"journal":{"name":"Proceedings of the ACM Recommender Systems Challenge 2018","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134551676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

Effective Nearest-Neighbor Music Recommendations 有效的近邻音乐推荐

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267474

Malte Ludewig, Iman Kamehkhosh, Nick Landia, D. Jannach

{"title":"Effective Nearest-Neighbor Music Recommendations","authors":"Malte Ludewig, Iman Kamehkhosh, Nick Landia, D. Jannach","doi":"10.1145/3267471.3267474","DOIUrl":"https://doi.org/10.1145/3267471.3267474","url":null,"abstract":"Automated recommendations for next tracks to listen to or to include in a playlist are a common feature on modern music platforms. Correspondingly, a variety of algorithmic approaches for determining tracks to recommend have been proposed in academic research. The most sophisticated among them are often based on conceptually complex learning techniques which can also require substantial computational resources or special-purpose hardware like GPUs. Recent research, however, showed that conceptually more simple techniques, e.g., based on nearest-neighbor schemes, can represent a viable alternative to such techniques in practice. In this paper, we describe a hybrid technique for next-track recommendation, which was evaluated in the context of the ACM RecSys 2018 Challenge. A combination of nearest-neighbor techniques, a standard matrix factorization algorithm, and a small set of heuristics led our team KAENEN to the 3rd place in the \"creative\" track and the 7th one in the \"main\" track, with accuracy results only a few percent below the winning teams. Given that offline prediction accuracy is only one of several possible quality factors in music recommendation, practitioners have to validate if slight accuracy improvements truly justify the use of highly complex algorithms in real-world applications.","PeriodicalId":430663,"journal":{"name":"Proceedings of the ACM Recommender Systems Challenge 2018","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125858132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 22

Using Adversarial Autoencoders for Multi-Modal Automatic Playlist Continuation 使用对抗性自动编码器进行多模态自动播放列表延续

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267476

Iacopo Vagliano, Lukas Galke, Florian Mai, A. Scherp

引用次数: 6

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267486

G. Faggioli, Mirko Polato, F. Aiolli

引用次数: 5

An Ensemble Approach of Recurrent Neural Networks using Pre-Trained Embeddings for Playlist Completion 使用预训练嵌入的循环神经网络集成方法用于播放列表补全

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267484

Diego Monti, Enrico Palumbo, Giuseppe Rizzo, Pasquale Lisena, Raphael Troncy, Michael Fell, Elena Cabrio, M. Morisio

{"title":"An Ensemble Approach of Recurrent Neural Networks using Pre-Trained Embeddings for Playlist Completion","authors":"Diego Monti, Enrico Palumbo, Giuseppe Rizzo, Pasquale Lisena, Raphael Troncy, Michael Fell, Elena Cabrio, M. Morisio","doi":"10.1145/3267471.3267484","DOIUrl":"https://doi.org/10.1145/3267471.3267484","url":null,"abstract":"This paper describes the approach of the D2KLab team to the RecSys Challenge 2018 that focuses on the task of playlist completion. We propose an ensemble strategy of different recurrent neural networks leveraging pre-trained embeddings representing tracks, artists, albums, and titles as inputs. We also use lyrics from which we extract semantic and stylistic features that we fed into the network for the creative track. The RNN learns a probabilistic model from the sequences of items in the playlist, which is then used to predict the most likely tracks to be added to the playlist. Concerning the playlists without tracks, we implemented a fall-back strategy called Title2Rec that generates recommendations using only the playlist title. We optimized the RNN, Title2Rec, and the ensemble approach on a validation set, tuning hyper-parameters such as the optimizer algorithm, the learning rate, and the generation strategy. This approach is effective in predicting tracks for a playlist and flexible to include diverse types of inputs, but it is also computationally demanding in the training phase.","PeriodicalId":430663,"journal":{"name":"Proceedings of the ACM Recommender Systems Challenge 2018","volume":"56 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121004546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

A hybrid two-stage recommender system for automatic playlist continuation 自动播放列表延续的混合两阶段推荐系统

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267488

V. Rubtsov, Mikhail Kamenshchikov, I. Valyaev, V. Leksin, D. Ignatov

引用次数: 9

TrailMix: An Ensemble Recommender System for Playlist Curation and Continuation TrailMix:一个用于播放列表管理和延续的集成推荐系统

Proceedings of the ACM Recommender Systems Challenge 2018 Pub Date : 2018-10-02 DOI: 10.1145/3267471.3267479

Xing Zhao, Qingquan Song, James Caverlee, Xia Hu

引用次数: 7