sisinflab Goto Github PK

iswc2017

kgflex

Official implementation of the paper "Sparse Feature Factorization for Recommender Systems with Knowledge Graphs"

kgtore

linkeddatasets

lodexposer

A Docker container with all you need to publish your data in the Linked Data Cloud. It comes with Fuseki, LodView and LodLive already installed.

lodreclib

lodreclib is a Java library to build recommendation engines which exploit the information encoded in Linked (Open) Data datasets.

lodrecsys-datasets

Here, we provide mappings to DBpedia resources of items in well known datasets to evaluate recommender systems. This can allows practitioners in the field to evaluate and compare their algorithms with existing approaches.

losm

Linked Open Street Map - a middleware to query OSM via SPARQL queries

msap

In this work, we extend the FGSM method proposing multistep adversarial perturbation (MSAP) procedures to study the recommenders’ robustness under powerful methods. Letting fixed the perturbation magnitude, we illustrate that MSAP is much more harmful than FGSM in corrupting the recommendation performance of BPR-MF.

multimodal-fairness

multimodal-feature-extractor

A Python implementation to extract multimodal features (visual and textual).

musica-humana

Progetto sviluppato in collaborazione fra Politecnico di Bari e Conservatorio di Matera

novelty-diversity-graph

Accepted as short paper at MORS2022@RecSys2022

papers-results

Papers Results

pareto-sensitivity

perceptual-rec-mutation-of-adv-vrs

Accepted at WDSC@NeurIPS2020

personal-lightgcn

poldo

A tool for exposing the deep Web in the Linked Data cloud

poldo-client

polibot

Polibot is a application for Windows (x64) developed to build an info point with voice interaction inside the Polytechnic University of Bari.

pursuing-privacy-tutorial

qalib

randomizedresponseforrecommendersystems

recommenders

Recommender Systems algorithms implementations

recsys2021-pursuing-privacy

Material supporting the tutorial "Pursuing Privacy in Recommender Systems: The View of Users and Researchers from Regulations to Applications" held at the 15th ACM Conference on Recommender Systems in Amsterdam, Netherlands

reenvisioning-the-comparison-between-neural-collaborative-filtering-and-matrix-factorization

roger

sac2017

Code and results for the paper : "Schema-summarization in Linked-Data-based feature selection for recommender systems"

sasha-against-cfrs

Semantics-Aware Shilling Attacks against collaborative recommender systems via Knowledge Graphs

semauto

A Java framework to build semantics-aware autoencoder neural network from a knowledge-graph.