@HercoleLab

Human-Explainable, Robust, and COllaborative LEarning Lab @ Sapienza University of Rome

Joined September 2021
  • Tweets18
  • Following35
  • Followers37
📢 Announcing #LLM4XAI: Generative Models for Explainable AI Narratives, organized by @HercoleLab and co-located with #CIKM2026 in Rome, Italy! Exploring how LLMs and generative AI can enable human-centered explanations by bridging #XAI, #NLP, and #HCI. 🌐 hercolelab.github.io/LLM4XAI…
1
1
312
🚨 Exciting News! 🚨 Our paper titled "Natural Language Counterfactual Explanations for Graphs Using Large Language Models" has been accepted at #AISTATS2025. Authors: #FlavioGiorgi, @caesar_one_, @fabreetseo, and @gtolomei arXiv preprint: arxiv.org/abs/2410.09295

Natural Language Counterfactual Explanations for Graphs Using...

Explainable Artificial Intelligence (XAI) has emerged as a critical area of research to unravel the opaque inner logic of (deep) machine learning models. Among the various XAI techniques proposed...

arxiv.org
1
5
168
🚨 Exciting News! 🚨 @edogab_acc - one our brilliant PhD students - will be presenting our secure Federated Learning framework, #FLANDERS, at the #FlowerMonthly hosted by @flwrlabs! 🌼 🗓️ Today at 6:00 p.m. 🔗 Don't miss it: flower.ai/join-flower-monthl… #FederatedLearning #Robust #AI
3
3
257
Great news! The leading open-source #FederatedLearning framework @flwrlabs is now integrating our robust aggregation filtering technique, #FLANDERS (flower.ai/docs/baselines/fla…). Huge achievement by @edogab_acc from our lab! Special thanks to @jafermarq from #Flower.
2
4
301
🎉Congrats to @jmp2esp for having his Master's thesis accepted at the @NG_AI_Safety workshop! 📎∇τ: Gradient-based and Task-Agnostic machine Unlearning arxiv.org/pdf/2403.14339 Joint work with researchers from @RSTLessGroup @caesar_one_ @mariasofiabuc @fabreetseo @gtolomei
6
1
12
457
rb.gy/9o6rp5 Not the video quality we were aiming for, but still, please watch this out to boost the view count of the promotional video for our #KDD2024 paper. @fabreetseo, @andreabe99 Let's go for a gazillion views!
1
3
240
+++Great News!+++ Our paper titled "Evading Community Detection via Counterfactual Neighborhood Search" has been accepted at #KDD2024 (Research Track). Stay tuned for more info and the preprint version of this amazing work by @andreabe99 @fabreetseo and @gtolomei
1
3
7
365
Please check out the preprint on arXiv: arxiv.org/abs/2310.08909

Evading Community Detection via Counterfactual Neighborhood Search

Community detection techniques are useful for social media platforms to discover tightly connected groups of users who share common interests. However, this functionality often comes at the...

arxiv.org
2
58
+++Ph.D. in Data Science at Sapienza: 2023-24 Call for Applications+++ Want to pursue a research career in Data Science at one of the most prestigious European Universities? Check out the call: phd.uniroma1.it/web/concorso… Application deadline: June 22, at 2 p.m. CEST
1
3
225
Please, check out the updated CfP at sites.google.com/view/flirt-… To submit your work, use the following link: easychair.org/my/conference?… @SIGIRConf #workshop #federatedlearning #FL #informationretrieval #IR

flirt-sigir23 - Call for Papers

TOPICS AND THEMES

sites.google.com
2
2
143
+++Submission Deadline Extension+++ Full papers due: A̶p̶r̶i̶l̶ ̶2̶5̶,̶ ̶2̶0̶2̶3̶ -> May 8, 2023 (AoE) @SIGIRConf #workshop #federatedlearning #FL #informationretrieval #IR
4
3
275
Your @sigir2023 full/short paper did not get in? Then you should flirt with the idea of submitting to FLIRT, the #1 workshop on Federated Learning for Information ReTrieval! details at: sites.google.com/view/flirt-…

flirt-sigir23

A wide range of core information retrieval (IR) tasks, such as searching, ranking, and filtering, to name a few, have seen tremendous improvements thanks to machine learning (ML) and artificial...

sites.google.com
6
8
673
The website of the FLIRT 2023 workshop is online: sites.google.com/view/flirt-… This is still a work in progress, so please stay tuned! @SIGIRConf #workshops

flirt-sigir23

A wide range of core information retrieval (IR) tasks, such as searching, ranking, and filtering, to name a few, have seen tremendous improvements thanks to machine learning (ML) and artificial...

sites.google.com
3
3
257
Great news! Our paper entitled "ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models" has been accepted at @cikm2022 Amazing joint work by @gtolomei, @fabreetseo, #ZihengChen #JiaWang, #HeZhu, and #HongshikAhn #CIKM2022 #XAI
2
2
4
Check the preprint of the paper if interested: arxiv.org/abs/2110.11960 @gtolomei @fabreetseo #CIKM2022 #XAI

ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary...

Counterfactual examples (CFs) are one of the most popular methods for attaching post-hoc explanations to machine learning (ML) models. However, existing CF generation methods either exploit the...

arxiv.org
1
1
Ever wonder why your favorite e-commerce website suggests buying that item? Our paper "GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations" tries to answer that! Accepted at #XKDD22 (preprint:arxiv.org/abs/2208.04222) @gtolomei @fabreetseo et al.
1
2
7
The 1st Workshop on Federated Learning for Private Web Search and Data Mining (FL4P-WSDM) will be hosted at ACM WSDM 2022. For more information, please visit the workshop website: fl4p-wsdm.github.io/
The Human-Explainable, Robust, and COllaborative LEarning Lab @ Sapienza University of Rome was officially launched on August 26, 2021! There's still a lot to be done (including finalizing our logo and website) but we'll surely get there! Please, stay tuned and spread the word!
2
Load more