Effective and secure federated online learning to rank

TL;DR

This paper explores federated online learning to rank, aiming to improve privacy, robustness, and security in ranking models that learn continually from user feedback without sharing raw data.

Contribution

It provides a comprehensive study on FOLTR, addressing its effectiveness, robustness, security, and unlearning, which advances the current state of privacy-preserving online ranking.

Findings

FOLTR enhances privacy by not sharing raw user data.

Challenges include maintaining ranking effectiveness and robustness across clients.

The study proposes solutions to improve security and unlearning in FOLTR.

Abstract

Online Learning to Rank (OLTR) optimises ranking models using implicit user feedback, such as clicks. Unlike traditional Learning to Rank (LTR) methods that rely on a static set of training data with relevance judgements to learn a ranking model, OLTR methods update the model continually as new data arrives. Thus, it addresses several drawbacks such as the high cost of human annotations, potential misalignment between user preferences and human judgments, and the rapid changes in user query intents. However, OLTR methods typically require the collection of searchable data, user queries, and clicks, which poses privacy concerns for users. Federated Online Learning to Rank (FOLTR) integrates OLTR within a Federated Learning (FL) framework to enhance privacy by not sharing raw data. While promising, FOLTR methods currently lag behind traditional centralised OLTR due to challenges in ranking effectiveness, robustness with respect to data distribution across clients, susceptibility to attacks, and the ability to unlearn client interactions and data. This thesis presents a comprehensive study on Federated Online Learning to Rank, addressing its effectiveness, robustness, security, and unlearning capabilities, thereby expanding the landscape of FOLTR.