Information Systems Lab @ Polytechnic University of Bari (@sisinflab)
Guthub

sisinflab

Twitter logo Share LinkedIn logo Share Facebook logo Share

Top repositories

1

elliot

Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluation
Python
264
star
2

adversarial-recommender-systems-survey

The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions. In this survey, we provide an exhaustive literature review of 74 articles published in major RS and ML journals and conferences. This review serves as a reference for the RS community, working on the security of RS or on generative models using GANs to improve their quality.
156
star
3

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.
31
star
4

amlrecsys-tutorial

Tutorial by Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia and Felice Antonio Merra about Adversarial Machine Learning in Recommender Systems
25
star
5

KGFlex

Official implementation of the paper "Sparse Feature Factorization for Recommender Systems with Knowledge Graphs"
Python
20
star
6

Reenvisioning-the-comparison-between-Neural-Collaborative-Filtering-and-Matrix-Factorization

Python
20
star
7

lodreclib

lodreclib is a Java library to build recommendation engines which exploit the information encoded in Linked (Open) Data datasets.
Java
18
star
8

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
Jupyter Notebook
18
star
9

FedBPR

Python
16
star
10

SEMAUTO-2.0

Semantics-Aware Autoencoder Neural Network
Python
15
star
11

HandsOn-ECIR2021

CSS
13
star
12

SEMAUTO

A Java framework to build semantics-aware autoencoder neural network from a knowledge-graph.
Java
13
star
13

Recommender-ChatGPT

The official source code and datasets for the paper titled "Evaluating ChatGPT as a Recommender System: A Rigorous Approach"
Python
12
star
14

LoG-2023-GNNs-RecSys

Presented as tutorial at the Second Learning on Graphs Conference (LoG 2023)
Jupyter Notebook
12
star
15

Formal-MultiMod-Rec

Formalizing Multimedia Recommendation through Multimodal Deep Learning, accepted in ACM Transactions on Recommender Systems.
Python
10
star
16

Graph-RSs-Reproducibility

Accepted as reproducibility paper at RecSys 2023.
Python
10
star
17

recommenders

Recommender Systems algorithms implementations
Java
8
star
18

LinkedDatasets

8
star
19

Top-N-Recommendation-Algorithms-A-Quest-for-the-State-of-the-Art

This is the official repository of the paper Top-N Recommendation Algorithms: A Quest for the State of the Art
Python
8
star
20

interactive-question-answering-systems-survey

A collection of work regarding Interactive Question Answering System standing over 10 years.
8
star
21

Ducho

Under review at The Web Conference 2024.
Python
7
star
22

Visual-Adversarial-Recommendation

we present an evaluation framework, named Visual Adversarial Recommender (\var), to empirically investigate the performance of defended or undefended DNNs in various visually-aware item recommendation tasks.
Python
6
star
23

KGTORe

Python
5
star
24

losm

Linked Open Street Map - a middleware to query OSM via SPARQL queries
Java
5
star
25

TimePOP

TimePop is a simple and efficient algorithm that combines the notion of personalized popularity and temporal aspects.
Java
4
star
26

Multimodal-Feature-Extractor

A Python implementation to extract multimodal features (visual and textual).
Python
4
star
27

Content-Style-VRSs

Official implementation of the paper "Leveraging Content-Style Item Representation for Visual Recommendation" accepted at ECIR 2022
Python
4
star
28

Interpretability-of-BERT-Latent-Space-through-Knowledge-Graphs

Here we present the code we implemented to interpret and explain the BERT language model through the latent space it generates. The work identifies a feasibility study of analyzing BERT's latent semantic space using a knowledge graph.
Python
4
star
29

MultiMod-Popularity-Bias

Accepted as full paper at MMIR @ ACM Multimedia 2023
Python
3
star
30

dlpreferences

Reasoning with preferences in Description Logics
Java
3
star
31

simlib

A Java framework for semantic similarity and relatedness metrics for Knowledge Graphs
Java
3
star
32

DatasetsSplits

This is a collection of splittings of publicly available Datasets. This collection has been created for two main purposes:
Java
3
star
33

iir2021

IIR 2021 | 11th Italian Information Retrieval Workshop
3
star
34

ClientAware-FL

Python
3
star
35

TAaMR

Targeted Adversarial Attack against Multimedia Recommender Systems (TAaMR) at DSML2020
Python
3
star
36

Augmented-and-Linked-Open-Datasets-for-Recommendation

Python
3
star
37

Graph-Characteristics

Python
3
star
38

qalib

Python
2
star
39

Edge-Graph-Collaborative-Filtering

Accepted as full paper at DL4SR@CIKM2022
Python
2
star
40

HybridFactorizationMachines

Java
2
star
41

SAC2017

Code and results for the paper : "Schema-summarization in Linked-Data-based feature selection for recommender systems"
Java
2
star
42

CNNs-in-VRSs

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
2
star
43

poldo

A tool for exposing the deep Web in the Linked Data cloud
Java
2
star
44

anna

Vocal Assistant / Chatbot Anna to explore Puglia Digital Library
2
star
45

The-importance-of-being-dissimilar-in-Recommendation

Similarity measures play a fundamental role in memory-based nearest neighbors approaches. They recommend items to a user based on the similarity of either items or users in a neighborhood. In this paper we argue that, although it keeps a leading importance in computing recommendations, similarity between users or items should be paired with a value of dissimilarity (computed not just as the complement of the similarity one). We formally modeled and injected this notion in some of the most used similarity measures and evaluated our approach showing its effectiveness in terms of accuracy results.
2
star
46

ECIR2023-Graph-CF

Accepted as full paper at ECIR 2023
Python
1
star
47

X-LOD-Lookup

Scala
1
star
48

RecMOE

A library to compute Pareto fronts and evaluate them using Quality Indicators (QIs) for Recommender Systems
Python
1
star
49

poldo-client

TypeScript
1
star
50

Features-Factorization

Features-Factorization and Feature Spreading Relevance (Knowledge-aware Recommender Systems)
Java
1
star
51

The-Idiosyncratic-Effects-of-Adversarial-Training

Code and Data for the #RecSys2021 article "The Idiosyncratic Effects of Adversarial Training on Bias in Personalized Recommendation Learning".
Python
1
star
52

LHider

Python
1
star
53

Topology-Graph-Collaborative-Filtering

Python
1
star
54

Perceptual-Rec-Mutation-of-Adv-VRs

Accepted at WDSC@NeurIPS2020
Python
1
star
55

Graph-Demo

Accepted as demo paper at UMAP 2023
Python
1
star
56

ISWC2017

1
star
57

X-LOD

A Content Management System to edit and publish your Linked Open Data. X-LOD has been inspired by the Wikidata project with RDF data and triplestores in mind.
CSS
1
star
58

MSAP

In this work, we extend the FGSM method proposing multistep adversarial perturbation (MSAP) procedures to study the recommendersโ€™ 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.
Python
1
star
59

KGUF

Python
1
star
60

Multimodal-RSs-Reproducibility

Python
1
star