DeepAI
Log In Sign Up

Faithfully Explaining Rankings in a News Recommender System

05/14/2018
by   Maartje ter Hoeve, et al.
0

There is an increasing demand for algorithms to explain their outcomes. So far, there is no method that explains the rankings produced by a ranking algorithm. To address this gap we propose LISTEN, a LISTwise ExplaiNer, to explain rankings produced by a ranking algorithm. To efficiently use LISTEN in production, we train a neural network to learn the underlying explanation space created by LISTEN; we call this model Q-LISTEN. We show that LISTEN produces faithful explanations and that Q-LISTEN is able to learn these explanations. Moreover, we show that LISTEN is safe to use in a real world environment: users of a news recommendation system do not behave significantly differently when they are exposed to explanations generated by LISTEN instead of manually generated explanations.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/30/2018

The Intriguing Properties of Model Explanations

Linear approximations to the decision boundary of a complex model have b...
05/27/2022

A Design Space for Explainable Ranking and Ranking Models

Item ranking systems support users in multi-criteria decision-making tas...
01/25/2023

ExaRanker: Explanation-Augmented Neural Ranker

Recent work has shown that inducing a large language model (LLM) to gene...
04/29/2020

Valid Explanations for Learning to Rank Models

Learning-to-rank (LTR) is a class of supervised learning techniques that...
11/27/2020

Reflective-Net: Learning from Explanations

Humans possess a remarkable capability to make fast, intuitive decisions...
07/19/2019

Greedy Optimized Multileaving for Personalization

Personalization plays an important role in many services. To evaluate pe...
01/30/2023

Explaining Dataset Changes for Semantic Data Versioning with Explain-Da-V (Technical Report)

In multi-user environments in which data science and analysis is collabo...