<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>DIN on Chen Kai Blog</title><link>https://www.chenk.top/en/tags/din/</link><description>Recent content in DIN on Chen Kai Blog</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 28 Dec 2025 09:00:00 +0000</lastBuildDate><atom:link href="https://www.chenk.top/en/tags/din/index.xml" rel="self" type="application/rss+xml"/><item><title>Recommendation Systems (10): Deep Interest Networks and Attention Mechanisms</title><link>https://www.chenk.top/en/recommendation-systems/10-deep-interest-networks/</link><pubDate>Sun, 28 Dec 2025 09:00:00 +0000</pubDate><guid>https://www.chenk.top/en/recommendation-systems/10-deep-interest-networks/</guid><description>&lt;p>A good chef doesn&amp;rsquo;t cook the same dish for every guest. She watches you walk in, notes the wine you order, and glances at how you eye the chalkboard — then decides whether tonight&amp;rsquo;s special should be the steak or the risotto. Your past visits matter, but only the parts that fit &lt;em>this&lt;/em> mood.&lt;/p>
&lt;p>A recommendation model used to be a worse chef. It would take everything the user had ever clicked, average it into a single vector, and serve the same dish to everyone in the room. The vintage leather jacket you viewed last week and the random phone charger you clicked six months ago carried equal weight, regardless of what you&amp;rsquo;re looking at now.&lt;/p></description></item></channel></rss>