Learning and Optimization of Implicit Negative Feedback for Industrial Short-video Recommender System

TL;DR

This paper introduces a novel industrial approach for short-video recommendation that effectively leverages implicit negative feedback, such as skipping behavior, to improve user interest modeling and multi-objective optimization at scale.

Contribution

The paper proposes a feedback-aware encoding and multi-objective prediction framework tailored for large-scale short-video recommendation systems, addressing implicit feedback challenges.

Findings

Effective extraction of user preferences from skipping behavior.

Improved recommendation performance verified through extensive online A/B testing.

Successful deployment in Kuaishou serving billion-level users.

Abstract

Short-video recommendation is one of the most important recommendation applications in today's industrial information systems. Compared with other recommendation tasks, the enormous amount of feedback is the most typical characteristic. Specifically, in short-video recommendation, the easiest-to-collect user feedback is the skipping behavior, which leads to two critical challenges for the recommendation model. First, the skipping behavior reflects implicit user preferences, and thus, it is challenging for interest extraction. Second, this kind of special feedback involves multiple objectives, such as total watching time and skipping rate, which is also very challenging. In this paper, we present our industrial solution in Kuaishou, which serves billion-level users every day. Specifically, we deploy a feedback-aware encoding module that extracts user preferences, taking the impact of context into consideration. We further design a multi-objective prediction module which well distinguishes the relation and differences among different model objectives in the short-video recommendation. We conduct extensive online A/B tests, along with detailed and careful analysis, which verify the effectiveness of our solution.