Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page
Demo Data from VLDB 2026 / reviewers in the wild / expert

Xianzhuo Xia

dblp:270/6433 · DBLP profile ↗
← Back
1ranked-venue papers
0as first author
0since 2021 · last 2020
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Databases, data management, data science and information retrieval · 1

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Trustworthy machine learning · 100%
Databases, data mining, and information retrieval
1 paper
Recommender systems · 100%

Topics — the 3 heaviest of 3, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Trustworthy machine learning › robustness
adversarial robustness		 0.412020
Certifiable Robustness to Discrete Adversarial Perturbations for Factorization Machines · SIGIR 2020
Machine learning › Trustworthy machine learning › robustness
certified robustness		 0.412020
Certifiable Robustness to Discrete Adversarial Perturbations for Factorization Machines · SIGIR 2020
Recommender systems › factorization models
factorization machines		 0.412020
Certifiable Robustness to Discrete Adversarial Perturbations for Factorization Machines · SIGIR 2020

Methods — techniques the papers use, named apart from their topics

robustness certification · 0.9randomized smoothing · 0.9
YearPublicationVenuePosition
2020 Certifiable Robustness to Discrete Adversarial Perturbations for Factorization Machines
abstract
Factorization machines (FMs) have been widely adopted to model the discrete feature interactions in recommender systems. Despite their great success, currently there is no study of their robustness to discrete adversarial perturbations. Whether modifying a certain number of the discrete input features has a dramatic effect on the FM's prediction? Although there exist robust training methods for FMs, they neglect the discrete property of input features and lack of an effective mechanism to verify the model robustness.
Yang Liu 0245, Xianzhuo Xia, Liang Chen 0001, Xiangnan He 0001, Carl Yang 0001, Zibin Zheng
 SIGIR2