136 citations · 448 across the 41 of their papers we have counts for
45 papers
CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training
Amine Lbath, Manan Suri, Aurelien Delaitre +4
Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software. Generally available a…
JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning
Ali Aghababaei-Harandi, Aude Sportisse, Massih-Reza Amini
Semi-supervised learning has emerged as a powerful paradigm for leveraging large amounts of unlabeled data to improve the performance of machine learning models when labeled data a…
Stylized Meta-Album: Group-bias injection with style transfer to study robustness against distribution shifts
Romain Mussard, Aurélien Gauffre, Ihsan Ullah +4
We introduce Stylized Meta-Album (SMA), a new image classification meta-dataset comprising 24 datasets (12 content datasets, and 12 stylized datasets), designed to advance studies…
AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset
Amine Lbath, Massih-Reza Amini, Aurelien Delaitre +1
The increasing complexity of software systems and the sophistication of cyber-attacks have underscored the need for reliable automated software vulnerability detection. Data-driven…
Multi-Label Contrastive Learning : A Comprehensive Study
Alexandre Audibert, Aurélien Gauffre, Massih-Reza Amini
Multi-label classification, which involves assigning multiple labels to a single input, has emerged as a key area in both research and industry due to its wide-ranging applications…
A Unified Contrastive Loss for Self-Training
Aurelien Gauffre, Julien Horvat, Massih-Reza Amini
Self-training methods have proven to be effective in exploiting abundant unlabeled data in semi-supervised learning, particularly when labeled data is scarce. While many of these a…
Unified Framework for Pre-trained Neural Network Compression via Decomposition and Optimized Rank Selection
Ali Aghababaei-Harandi, Massih-Reza Amini
Despite their high accuracy, complex neural networks demand significant computational resources, posing challenges for deployment on resource constrained devices such as mobile pho…
Classification Tree-based Active Learning: A Wrapper Approach
Ashna Jose, Emilie Devijver, Massih-Reza Amini +2
Supervised machine learning often requires large training sets to train accurate models, yet obtaining large amounts of labeled data is not always feasible. Hence, it becomes cruci…
Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification
Alexandre Audibert, Aurélien Gauffre, Massih-Reza Amini
Learning an effective representation in multi-label text classification (MLTC) is a significant challenge in NLP. This challenge arises from the inherent complexity of the task, wh…
Pool-Based Active Learning with Proper Topological Regions
Lies Hadjadj, Emilie Devijver, Remi Molinier +1
Machine learning methods usually rely on large sample size to have good performance, while it is difficult to provide labeled set in many applications. Pool-based active learning m…
Deep Learning with Partially Labeled Data for Radio Map Reconstruction
Alkesandra Malkova, Massih-Reza Amini, Benoit Denis +1
In this paper, we address the problem of Received Signal Strength map reconstruction based on location-dependent radio measurements and utilizing side knowledge about the local reg…
Ranking-Based Physics-Informed Line Failure Detection in Power Grids
Aleksandra Burashnikova, Wenting Li, Massih Amini +2
Climate change increases the number of extreme weather events (wind and snowstorms, heavy rains, wildfires) that compromise power system reliability and lead to multiple equipment…
Generalization bounds for learning under graph-dependence: A survey
Rui-Ray Zhang, Massih-Reza Amini
Traditional statistical learning theory relies on the assumption that data are identically and independently distributed (i.i.d.). However, this assumption often does not hold in m…
Learning over No-Preferred and Preferred Sequence of Items for Robust Recommendation (Extended Abstract)
Aleksandra Burashnikova, Yury Maximov, Marianne Clausel +3
This paper is an extended version of [Burashnikova et al., 2021, arXiv: 2012.06910], where we proposed a theoretically supported sequential strategy for training a large-scale Reco…
Self-Training: A Survey
Massih-Reza Amini, Vasilii Feofanov, Loic Pauletto +3
Semi-supervised algorithms aim to learn prediction functions from a small set of labeled observations and a large set of unlabeled observations. Because this framework is relevant…
Self Semi Supervised Neural Architecture Search for Semantic Segmentation
Loïc Pauletto, Massih-Reza Amini, Nicolas Winckler
In this paper, we propose a Neural Architecture Search strategy based on self supervision and semi-supervised learning for the task of semantic segmentation. Our approach builds an…
Recommender systems: when memory matters
Aleksandra Burashnikova, Marianne Clausel, Massih-Reza Amini +2
In this paper, we study the effect of long memory in the learnability of a sequential recommender system including users' implicit feedback. We propose an online algorithm, where m…
Bilingual Topic Models for Comparable Corpora
Georgios Balikas, Massih-Reza Amini, Marianne Clausel
Probabilistic topic models like Latent Dirichlet Allocation (LDA) have been previously extended to the bilingual setting. A fundamental modeling assumption in several of these exte…
A Large Scale Benchmark for Individual Treatment Effect Prediction and Uplift Modeling
Eustache Diemert, Artem Betlei, Christophe Renaudin +3
Individual Treatment Effect (ITE) prediction is an important area of research in machine learning which aims at explaining and estimating the causal impact of an action at the gran…
Self-Training of Halfspaces with Generalization Guarantees under Massart Mislabeling Noise Model
Lies Hadjadj, Massih-Reza Amini, Sana Louhichi +1
We investigate the generalization properties of a self-training algorithm with halfspaces. The approach learns a list of halfspaces iteratively from labeled and unlabeled training…
Multi-class Probabilistic Bounds for Self-learning
Vasilii Feofanov, Emilie Devijver, Massih-Reza Amini
Self-learning is a classical approach for learning with both labeled and unlabeled observations which consists in giving pseudo-labels to unlabeled training instances with a confid…
Self-Learning for Received Signal Strength Map Reconstruction with Neural Architecture Search
Aleksandra Malkova, Loic Pauletto, Christophe Villien +2
In this paper, we present a Neural Network (NN) model based on Neural Architecture Search (NAS) and self-learning for received signal strength (RSS) map reconstruction out of spars…
Treatment Targeting by AUUC Maximization with Generalization Guarantees
Artem Betlei, Eustache Diemert, Massih-Reza Amini
We consider the task of optimizing treatment assignment based on individual treatment effect prediction. This task is found in many applications such as personalized medicine or ta…
Learning over no-Preferred and Preferred Sequence of items for Robust Recommendation
Aleksandra Burashnikova, Marianne Clausel, Charlotte Laclau +3
In this paper, we propose a theoretically founded sequential strategy for training large-scale Recommender Systems (RS) over implicit feedback, mainly in the form of clicks. The pr…