User preference and embedding learning with implicit feedback for recommender systems
In this paper, we propose a novel ranking framework for collaborative filtering with the
overall aim of learning user preferences over items by minimizing a pairwise ranking loss …
overall aim of learning user preferences over items by minimizing a pairwise ranking loss …
[PDF][PDF] 个性化广告推荐系统及其应用研究
张玉洁, 董政, 孟祥武 - 计算机学报, 2021 - cjc.ict.ac.cn
摘要近年来, 随着互联网及智能移动设备的发展和普及, 丰富了广告的推送方式和投放平台.
但是传统的广告推送无法满足用户对个性化广告的需求, 导致用户对广告产生抵触情绪 …
但是传统的广告推送无法满足用户对个性化广告的需求, 导致用户对广告产生抵触情绪 …
Approximate distinct counts for billions of datasets
D Ting - Proceedings of the 2019 International Conference on …, 2019 - dl.acm.org
Cardinality estimation plays an important role in processing big data. We consider the
challenging problem of computing millions or more distinct count aggregations in a single …
challenging problem of computing millions or more distinct count aggregations in a single …
Learning to be a statistician: learned estimator for number of distinct values
Estimating the number of distinct values (NDV) in a column is useful for many tasks in
database systems, such as columnstore compression and data profiling. In this work, we …
database systems, such as columnstore compression and data profiling. In this work, we …
Learning to recommend diverse items over implicit feedback on PANDOR
In this paper, we present a novel and publicly available dataset for online recommendation
provided by Purch1. The dataset records the clicks generated by users of one of Purch's …
provided by Purch1. The dataset records the clicks generated by users of one of Purch's …
Neukron: Constant-size lossy compression of sparse reorderable matrices and tensors
Many real-world data are naturally represented as a sparse reorderable matrix, whose rows
and columns can be arbitrarily ordered (eg, the adjacency matrix of a bipartite graph) …
and columns can be arbitrarily ordered (eg, the adjacency matrix of a bipartite graph) …
Learning-based Property Estimation with Polynomials
The problem of estimating data properties using sampling frequency histograms has
attracted extensive interest in the area of databases. The properties include the number of …
attracted extensive interest in the area of databases. The properties include the number of …
An Efficient and Scalable Approach to Build Co-occurrence Matrix for DNN's Embedding Layer
Q Petit, C Li, N Emad - Proceedings of the 38th ACM International …, 2024 - dl.acm.org
Embedding is a crucial step for deep neural networks. Datasets, from different applications,
with different structures, can all be processed through an embedding layer and transformed …
with different structures, can all be processed through an embedding layer and transformed …
Sampling Space-Saving Set Sketches
Large, distributed data streams are now ubiquitous. High-accuracy sketches with low
memory overhead have become the de facto method for analyzing this data. For instance, if …
memory overhead have become the de facto method for analyzing this data. For instance, if …
Reverse-safe text indexing
We introduce the notion of reverse-safe data structures. These are data structures that
prevent the reconstruction of the data they encode (ie, they cannot be easily reversed). A …
prevent the reconstruction of the data they encode (ie, they cannot be easily reversed). A …