1,546 Hits in 5.5 sec

Sequential modeling of Sessions using Recurrent Neural Networks for Skip Prediction [article]

Sainath Adapa
2019 arXiv   pre-print
Recommender systems play an essential role in music streaming services, prominently in the form of personalized playlists.  ...  The proposed model initially generates a fixed vector representation of the session, and this additional information is incorporated into an Encoder-Decoder style architecture.  ...  Considering the large size of the dataset, the coupons were especially helpful.  ... 
arXiv:1904.10273v1 fatcat:7gczans6fvfrhblxukz45hd3xi

Attend to Chords: Improving Harmonic Analysis of Symbolic Music Using Transformer-Based Models

Tsung-Ping Chen, Li Su
2021 Transactions of the International Society for Music Information Retrieval  
Recently, two advanced models, namely the Bi-directional Transformer for Chord Recognition (BTC) and the Harmony Transformer (HT), introduced for the first time the multi-head attention mechanism to ACR  ...  These issues hinder the developments of music analysis and music generation via ACR systems.  ...  Acknowledgements We thank the editor and the anonymous reviewers for their insightful comments.  ... 
doi:10.5334/tismir.65 fatcat:bdqqj4evazbhzfc6blfjxs5syu

Generating Convincing Harmony Parts with Simple Long Short-Term Memory Networks

Andrei Faitas, Synne Engdahl Baumann, Torgrim Rudland Naess, Jim Torresen, Charles Patrick Martin
2019 Zenodo  
Generating convincing music via deep neural networks is a challenging problem that shows promise for many applications including interactive musical creation.  ...  Both of these are fairly dated models, as part of the investigation is to see what can be achieved with such models.  ...  It was also supported by by the Research Council of Norway and the Norwegian Centre for International Cooperation in Education as a part of the Collaboration on Intelligent Machines (COINMAC) project,  ... 
doi:10.5281/zenodo.3672979 fatcat:7h6qbnqwiva53d52zyy4fd3waa

User behavior understanding in real world settings [article]

Weiqi Shao, Xu Chen, Jiashu Zhao, Long Xia, Dawei Yin
2022 arXiv   pre-print
The IRC module learns the overall sequential characteristics of user behavior with a bi-directional architecture transformer.  ...  In this paper we propose a model that can automatically and adaptively generates a dynamic group of representations from the user behavior accordingly.  ...  Q1 • What are the effects of the bi-directional architecture transformer and the sequential recommender model Attention-GRU in behavior allocator?  ... 
arXiv:2112.02812v3 fatcat:ai6q2onxbzar7kd2fqdy5spmia

Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer [article]

Ziwei Fan and Zhiwei Liu and Jiawei Zhang and Yun Xiong and Lei Zheng and Philip S. Yu
2021 arXiv   pre-print
In order to model the evolution of user preference, we should learn user/item embeddings based on time-ordered item purchasing sequences, which is defined as Sequential Recommendation (SR) problem.  ...  Hence, we design a new framework Temporal Graph Sequential Recommender (TGSRec) upon our defined continuous-time bi-partite graph.  ...  This work is also funded in part by the National Natural Science Foundation of China Projects No. U1936213  ... 
arXiv:2108.06625v2 fatcat:nyv6p6hhebbqbnnohcy2aqkoau

Graph Neural Networks in Recommender Systems: A Survey

Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, Bin Cui
2022 ACM Computing Surveys  
Specifically, we provide a taxonomy of GNN-based recommendation models according to the types of information used and recommendation tasks.  ...  In recommender systems, the main challenge is to learn the effective user/item representations from their interactions and side information (if any).  ...  ACKNOWLEDGEMENT This work is supported by NSFC (No. 61832001), Beijing Academy of Artiicial Intelligence (BAAI), and PKU-Tencent Joint Research Lab.  ... 
doi:10.1145/3535101 fatcat:hgv2tbx3k5hzbnkupwsysqwjmy

Deep Learning in Music Recommendation Systems

Markus Schedl
2019 Frontiers in Applied Mathematics and Statistics  
Latent item factors are commonly integrated into content-based filtering and hybrid MRS, whereas sequence models of music items are used for sequential music recommendation, e.g., automatic playlist continuation  ...  Deep neural networks are used in this domain particularly for extracting latent factors of music items from audio signals or metadata and for learning sequential patterns of music items (tracks or artists  ...  for automatic music playlist continuation, i.e., sequential music recommendation, and (3) extracting latent factors from user-item rating data to incorporate into CF models.  ... 
doi:10.3389/fams.2019.00044 fatcat:vvosxlygrravloyrj3qubflnoe

Graph Neural Networks in Recommender Systems: A Survey [article]

Shiwen Wu, Fei Sun, Wentao Zhang, Xu Xie, Bin Cui
2022 arXiv   pre-print
Specifically, we provide a taxonomy of GNN-based recommendation models according to the types of information used and recommendation tasks.  ...  In recommender systems, the main challenge is to learn the effective user/item representations from their interactions and side information (if any).  ...  Nevertheless, providing a unified framework to model the abundant data in recommendation applications is only part of the reason for the widespread adoption of GNN in recommender systems.  ... 
arXiv:2011.02260v4 fatcat:hvk22yyid5bzjnzmzchyti25ja

Gumble Softmax For User Behavior Modeling [article]

Weiqi Shao and Xu Chen and Jiashu Zhao and Long Xia and Dawei Yin
2022 arXiv   pre-print
We propose a sequential model with dynamic number of representations for recommendation systems (RDRSR).  ...  Current methods in sequential recommendation focus on learning a fixed number of representations for each user at any time, with a single representation or multi representations for the user.  ...  CONCLUSION In this article, we learning a dynamic group of representations for user to improve the performance of the sequential recommender system.  ... 
arXiv:2112.02787v2 fatcat:kfxm3o5wqfabzfs7cq2krggcde

Sequential Modelling with Applications to Music Recommendation, Fact-Checking, and Speed Reading [article]

Christian Hansen
2021 arXiv   pre-print
This thesis makes methodological contributions and new investigations of sequential modelling for the specific application areas of systems that recommend music tracks to listeners and systems that process  ...  Sequential modelling entails making sense of sequential data, which naturally occurs in a wide array of domains.  ...  Given the sequential nature of music consumption wherein the user sequentially decides to stream or skip the recommended music, it is not straightforward to recommend a track solely for the purpose of  ... 
arXiv:2109.06736v1 fatcat:xawmkvzhgng3vhhrs5xvwokqna

AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue [article]

Gaurav Kumar, Rishabh Joshi, Jaspreet Singh, Promod Yenigalla
2019 arXiv   pre-print
A stream of this network also utilizes transfer learning by pre-training a bidirectional transformer to extract semantic representation for each input sentence and incorporates external knowledge through  ...  in a chit-chat system.  ...  The sentence representation S ∈ R m×k is then passed to a Bi-GRU to obtain the representation S gru ∈ R m×dgru , where d gru is the dimension of the hidden state of Bi-GRU.  ... 
arXiv:1912.10160v1 fatcat:xhmmpnsz2fbqtexdhuhgk7p3a4

Multimodal Emotion Recognition from Art Using Sequential Co-Attention

Tsegaye Misikir Tashu, Sakina Hajiyeva, Tomas Horvath
2021 Journal of Imaging  
The resulting system can be used to categorize artworks according to the emotions they evoke; recommend paintings that accentuate or balance a particular mood; search for paintings of a particular style  ...  The proposed architecture helps the model to focus on learning informative and refined representations for both feature extraction and modality fusion.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/jimaging7080157 pmid:34460793 pmcid:PMC8404915 fatcat:xktlzcr2zbc4rdb6tlk6uhh46i

Fusing Knowledge and Aspect Sentiment for Explainable Recommendation

Peng Bai, Yang Xia, Yongsheng Xia
2020 IEEE Access  
Our model has a knowledge encoder (i.e. a Transformer encoder), which can encode knowledge into a high-level representation U. Next, we introduce content fusion in our model.  ...  The overall structure of this model is relatively simple. We use Bidirectional Encoder Representations from Transformers (BERT) [33] to do ABSA.  ... 
doi:10.1109/access.2020.3012347 fatcat:ifnchobdj5h4xekxykmrrz2nly

Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations [article]

Hui Fang, Danning Zhang, Yiheng Shu, Guibing Guo
2020 arXiv   pre-print
However, there is little systematic study on DL-based methods, especially regarding to how to design an effective DL model for sequential recommendation.  ...  In this view, this survey focuses on DL-based sequential recommender systems by taking the aforementioned issues into consideration.  ...  [86] incorporated vanilla attention with a Bi-GRU network to model user's short-term interest for music recommendation.  ... 
arXiv:1905.01997v3 fatcat:i7hvdiqjpnaupcq2osrblttb4u

A Survey on Knowledge Graph-Based Recommender Systems [article]

Qingyu Guo, Fuzhen Zhuang, Chuan Qin, Hengshu Zhu, Xing Xie, Hui Xiong, Qing He
2020 arXiv   pre-print
To solve the information explosion problem and enhance user experience in various online applications, recommender systems have been developed to model users preferences.  ...  In this paper, we conduct a systematical survey of knowledge graph-based recommender systems. We collect recently published papers in this field and summarize them from two perspectives.  ...  Last.FM [118] is the most popular dataset for music recommendation. The dataset contains information about users and their music listening records from the online music system [119] .  ... 
arXiv:2003.00911v1 fatcat:qhyca7pu3beqtk6x55kpggowea
« Previous Showing results 1 — 15 out of 1,546 results