LibRec 精选LibRec智能推荐 第 38 期（至2019.8.8），更新 12 篇精选内容。
醉后不知天在水，满船清梦压星河。
近期热点论文


1. Evaluating Recommender System Algorithms for Generating Local Music PlaylistsDaniel Akimchuk, Timothy Clerico, Douglas Turnbullhttps://arxiv.org/abs/1907.08687We explore the task of local music recommendation: provide listeners with personalized playlists of relevant tracks by artists who play most of their live events within a small geographic area. In this paper, we compare the performance of three standard recommender system algorithms (Item-Item Neighborhood (IIN), Alternating Least Squares for Implicit Feedback (ALS), and Bayesian Personalized Ranking (BPR)) on the task of local music recommendation using the Million Playlist Dataset. Despite the fact that techniques based on matrix factorization (ALS, BPR) typically perform best on large recommendation tasks, we find that the neighborhood-based approach (IIN) performs best for long-tail local music recommendation.
2. Recommender Systems with Heterogeneous Side InformationTianqiao Liu, Zhiwei Wang, Jiliang Tang, Songfan Yang, Gale Yan Huang, Zitao Liuhttps://arxiv.org/abs/1907.08679In modern recommender systems, both users and items are associated with rich side information, which can help understand users and items. Such information is typically heterogeneous and can be roughly categorized into flat and hierarchical side information. In this paper, we investigate the problem of exploiting heterogeneous side information for recommendations. Specifically, we propose a novel framework jointly captures flat and hierarchical side information with mathematical coherence. Empirical results show that our approach is able to lead a significant performance gain over the state-of-the-art methods.
3. Deep Learning to Address Candidate Generation and Cold Start Challenges in Recommender Systems: A Research SurveyKiran Rama, Pradeep Kumar, Bharat Bhaskerhttps://arxiv.org/abs/1907.08674Among the machine learning applications to business, recommender systems would take one of the top places when it comes to success and adoption. They help the user in accelerating the process of search while helping businesses maximize sales. Our paper addresses the gaps of providing a taxonomy of deep learning approaches to address recommender systems problems in the areas of cold start and candidate generation in recommender systems. We also summarize the advantages and limitations of these techniques while outlining areas for future research. 
4. Neural Cross-Domain Collaborative Filtering with Shared EntitiesVijaikumar M, Shirish Shevade, M N Murtyhttps://arxiv.org/abs/1907.08440Cross-Domain Collaborative Filtering (CDCF) provides a way to alleviate data sparsity and cold-start problems present in recommendation systems by exploiting the knowledge from related domains. In this work, we propose an end-to-end neural network model -- NeuCDCF, to address these challenges in a cross-domain setting. More importantly, NeuCDCF follows a wide and deep framework and it learns the representations combinedly from both matrix factorization and deep neural networks. We perform experiments on four real-world datasets and demonstrate that our model performs better than state-of-the-art CDCF models.
5. Block based Singular Value Decomposition approach to matrix factorization for recommender systemsPrasad Bhavana, Vikas Kumar, Vineet Padmanabhanhttps://arxiv.org/abs/1907.07410With the abundance of data in recent years, interesting challenges are posed in the area of recommender systems. Producing high quality recommendations with scalability and performance is the need of the hour. In this paper, we extend the SVD technique further for scalability and performance in the context of 1) multi-threading 2) multiple computational units (with the use of Graphical Processing Units) and 3) distributed computation. We used Compute Unified Device Architecture (CUDA) platform and related hardware for leveraging Graphical Processing Unit (GPU) along with block based SVD to demonstrate the advantages in terms of performance and memory.
6. Decentralized & Collaborative AI on BlockchainJustin D. Harris, Bo Waggonerhttps://arxiv.org/abs/1907.07247Machine learning has recently enabled large advances in artificial intelligence, but these tend to be highly centralized. We propose a framework for participants to collaboratively build a dataset and use smart contracts to host a continuously updated model. This model will be shared publicly on a blockchain where it can be free to use for inference. Ideal learning problems include scenarios where a model is used many times for similar input such as personal assistants, playing games, recommender systems, etc. A free and open source implementation for the Ethereum blockchain is provided at https://github.com/microsoft/0xDeCA10B.
7. On the Value of Bandit Feedback for Offline Recommender System EvaluationOlivier Jeunen, David Rohde, Flavian Vasilehttps://arxiv.org/abs/1907.12384In academic literature, recommender systems are often evaluated on the task of next-item prediction. The procedure aims to give an answer to the question: "Given the natural sequence of user-item interactions up to time t, can we predict which item the user will interact with at time t+1?".  From a causal perspective, the system performs an intervention, and we want to measure its effect. Next-item prediction is often used as a fall-back objective when information about interventions and their effects (shown recommendations and whether they received a click) is unavailable. Through a series of simulated experiments with the RecoGym environment, we show where traditional offline evaluation schemes fall short.

8. Completing partial recipes using item-based collaborative filtering to recommend ingredientsPaula Fermín Cueto, Meeke Roet, Agnieszka Słowikhttps://arxiv.org/abs/1907.12380Increased public interest in healthy life>










长按二维码向我转账


受苹果公司新规定影响，微信 iOS 版的赞赏功能被关闭，可通过二维码转账支持公众号。

















已同步到看一看



取消
发送


我知道了








朋友会在“发现-看一看”看到你“在看”的内容
确定













已同步到看一看写下你的想法



最多200字，当前共字
发送







已发送







朋友将在看一看看到
确定



写下你的想法...









取消
发布到看一看
确定




最多200字，当前共字








发送中













微信扫一扫
使用小程序







取消
允许






即将打开一个新页面

取消
允许