当前位置:网站首页>Kdd2022 | what features are effective for interaction?
Kdd2022 | what features are effective for interaction?
2022-07-04 22:09:00 【Zhiyuan community】
Paper title :
Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
Thesis link :
https://arxiv.org/pdf/2206.13764.pdf
Code :
https://github.com/ruizhangai/HIRS_Hypergraph_Infomax_Recommender_System.git
This paper mainly puts forward the relevant methods for feature interaction in Recommendation System , If all possible features are interacted , That consumption is great , In this paper, HIRS Used to directly generate beneficial feature interactions . The number of generated feature interactions can be specified to be much smaller than the number of all possible interactions , Therefore, the running time of the model is shorter .
In this paper, the concepts of hypergraph and mutual information are used to automatically generate effective feature interaction . Take the features in the sample as nodes , If there is interaction between features, there are superedges between these feature nodes .
First , After obtaining the sample , Take the sample characteristics as nodes , Map to the corresponding embedding, The edge set is empty Utilization node embedding Predicted super edge set Use nodes and super edges to predict the results of the recommendation system Some points need to be considered in the process of Super Edge prediction , For example, if the generated interaction is beneficial and effective , The resulting super edge matrix takes 0,1 sparse , So for these problems , The author makes corresponding improvements based on mutual information .
边栏推荐
- 面试题 01.01. 判定字符是否唯一
- [optimtool.unconstrained] unconstrained optimization toolbox
- 电话加密,中间4为****代替
- HDU - 1078 FatMouse and Cheese(记忆化搜索DP)
- gtest从一无所知到熟练使用(2)什么是测试夹具/装置(test fixture)
- TCP shakes hands three times and waves four times. Do you really understand?
- 力扣_回文数
- DevEco Device Tool 3.0 Release带来5大能力升级,让智能设备开发更高效
- 283. 移动零-c与语言辅助数组法
- New intersectionobserver usage notes
猜你喜欢
Radio and television Wuzhou signed a cooperation agreement with Huawei to jointly promote the sustainable development of shengteng AI industry
[leetcode] 17. Letter combination of telephone number
Cloudcompare & open3d DBSCAN clustering (non plug-in)
开源之夏专访|Apache IoTDB社区 新晋Committer谢其骏
机器学习笔记 - 互信息Mutual Information
Super detailed tutorial, an introduction to istio Architecture Principle and practical application
保证接口数据安全的10种方案
Master the use of auto analyze in data warehouse
Deveco device tool 3.0 release brings five capability upgrades to make intelligent device development more efficient
凭借了这份 pdf,最终拿到了阿里,字节,百度等八家大厂 offer
随机推荐
服务线上治理
Exclusive interview of open source summer | new committer Xie Qijun of Apache iotdb community
Bookmark
283. 移动零-c与语言辅助数组法
Spatiotemporal prediction 3-graph transformer
ArcGIS 10.2.2 | solution to the failure of ArcGIS license server to start
Rotary transformer string judgment
# 2156. Find the substring of the given hash value - post order traversal
Drop down selection of Ehlib database records
Implementation rules for archiving assessment materials of robot related courses 2022 version
广电五舟与华为签署合作协议,共同推进昇腾AI产业持续发展
并发优化总结
开户哪家券商比较好?网上开户安全吗
Application practice | Shuhai supply chain construction of data center based on Apache Doris
bizchart+slider实现分组柱状图
How is the entered query SQL statement executed?
更强的 JsonPath 兼容性及性能测试之2022版(Snack3,Fastjson2,jayway.jsonpath)
Master the use of auto analyze in data warehouse
力扣_回文数
HDU - 2859 Phalanx(DP)