将用户反馈纳入ML模型 [英] Incorporating user feedback in a ML model
问题描述
我已经为分类(0/1)NLP任务开发了ML模型，并将其部署在生产环境中.该模型的预测将显示给用户，并且用户可以选择提供反馈(如果预测正确/错误).
I have developed a ML model for a classification (0/1) NLP task and deployed it in production environment. The prediction of the model is displayed to users, and the users have the option to give a feedback (if the prediction was right/wrong).
如何将这些反馈持续纳入我的模型中?从UX的角度来看，您不希望用户针对特定输入对系统进行两次更正/教导(两次/三次)，系统学习得很快，也就是说，反馈将快速"地并入. (Google优先收件箱以无缝方式完成此操作)
How can I continuously incorporate this feedback in my model ? From a UX stand point you dont want a user to correct/teach the system more than twice/thrice for a specific input, system shld learn fast i.e. so the feedback shld be incorporated "fast". (Google priority inbox does this in a seamless way)
一个人如何构建这种反馈回路"，我的系统可以利用它进行改进?我在网上进行了大量搜索，但找不到相关材料.任何指针都会有很大的帮助.
How does one build this "feedback loop" using which my system can improve ? I have searched a lot on net but could not find relevant material. any pointers will be of great help.
请不要说通过包括新的数据点从头开始重新训练模型.那肯定不是谷歌和Facebook如何构建其智能系统的
Pls dont say retrain the model from scratch by including new data points. Thats surely not how google and facebook build their smart systems
要进一步解释我的问题，请考虑一下Google的垃圾邮件检测器，其优先收件箱或它们最近的智能回复"功能.他们具有学习/合并(快速)用户供稿的能力是众所周知的事实.
To further explain my question - think of google's spam detector or their priority inbox or their recent feature of "smart replies". Its a well known fact that they have the ability to learn / incorporate (fast) user feed.
始终保持快速的用户反馈(即用户必须教系统每个数据点最多2-3次正确的输出，并且系统开始为该数据点提供正确的输出)，并且确保它保持旧的学习并且在合并来自新数据点的学习内容时，不会在旧数据点(较早给出正确的输出)上开始提供错误的输出.
我还没有找到关于如何构建这样的系统的博客/文献/讨论，这是ML系统中以detaieedback循环解释的智能系统
希望我的问题现在更加清楚了.
Hope my question is little more clear now.
更新:我发现的一些相关问题是:
Update: Some related questions I found are:
https://datascience.stackexchange.com/questions/1073/在线机器学习图书馆
http://mlwave.com/预测在线机器学习的点击率/
https://en.wikipedia.org/wiki/Concept_drift
更新:我仍然没有具体答案，但是确实存在这样的食谱.阅读以下博客机器学习！=学习机.在本文中，Jean谈到了向机器添加反馈摄取循环".在此处中， 4 .
Update: I still dont have a concrete answer but such a recipe does exists. Read the section "Learning from the feedback" in the following blog Machine Learning != Learning Machine. In this Jean talks about "adding a feedback ingestion loop to machine". Same in here, here, here4.
推荐答案
构建一个简单，轻便的模型，可以根据反馈进行更新.在线机器学习为此提供了许多候选人
Build a simple, light model(s) that can be updated per feedback. Online Machine learning gives a number of candidates for this
大多数好的在线分类器都是线性的.在这种情况下，我们可以有两个，并通过一个小的浅层神经网络将它们组合起来，从而实现非线性.
Most good online classifiers are linear. In which case we can have a couple of them and achieve non-linearity by combining them via a small shallow neural net
https://stats.stackexchange.com/questions /126546/非线性动态在线分类寻找算法
这篇关于将用户反馈纳入ML模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
