2 citations · 6 across the 20 of their papers we have counts for
22 papers
Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models
Farooq Ahmad Wani, Maria Sofia Bucarelli, Mujtaba Hussain Mirza +5
Vision-language models (VLMs) are fragile under image corruption. We find that the wording of the question affects VLMs in two opposite ways. Verbose questions make VLMs substantia…
QUORUM: QUality-Optimized Routing Using Multiple annotators
Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu +2
Data annotation remains a central bottleneck in natural language processing, requiring human effort to obtain high-quality labels at scale. While Large Language Models (LLMs) offer…
Compositional Generalization in Autoregressive Models via Logit Composition
Aakash Kumar, Maria Sofia Bucarelli, Emanuele Natale
Composing autoregressive models remains a core challenge in understanding how large language models can combine behaviors or skills learned across tasks. We introduce a new and pri…
Select, Label, Evaluate: Active Testing in NLP
Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu +2
Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requ…
Same Answer, Different Representations: Hidden instability in VLMs
Farooq Ahmad Wani, Alessandro Suglia, Rohit Saxena +6
The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions reflect stable multimodal processi…
PISA: Prioritized Invariant Subgraph Aggregation for Out-of-Distribution Generalization on Graphs
Ali Ghasemi, Farooq Ahmad Wani, Maria Sofia Bucarelli +1
Invariant learning on graphs aims to build predictors that rely on causal substructures rather than on environment-specific shortcuts. Current methods extract either a single invar…
Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic
Mostafa Mozafari, Farooq Ahmad Wani, Maria Sofia Bucarelli +1
Corrupted training data are ubiquitous. Corrective Machine Unlearning (CMU) seeks to remove the influence of such corruption post-training. Prior CMU typically assumes access to id…
On Task Vectors and Gradients
Luca Zhou, Daniele Solombrino, Donato Crisostomi +4
Task arithmetic has emerged as a simple yet powerful technique for model merging, enabling the combination of multiple finetuned models into one. Despite its empirical success, a c…
Early-Exit Graph Neural Networks
Andrea Giuseppe Di Francesco, Maria Sofia Bucarelli, Franco Maria Nardini +3
Early-exit mechanisms allow deep neural networks to stop inference once prediction confidence is high, reducing latency and energy on easy inputs while retaining full-depth accurac…
MASS: MoErging through Adaptive Subspace Selection
Donato Crisostomi, Alessandro Zirilli, Antonio Andrea Gargiulo +5
Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training over…
The Majority Vote Paradigm Shift: When Popular Meets Optimal
Antonio Purificato, Maria Sofia Bucarelli, Anil Kumar Nelakanti +3
Reliably labelling data typically requires annotations from multiple human workers. However, humans are far from being perfect. Hence, it is a common practice to aggregate labels g…
Energy Guided smoothness to improve Robustness in Graph Classification
Farooq Ahmad Wani, Maria Sofia Bucarelli, Andrea Giuseppe Di Francesco +2
Graph Neural Networks (GNNs) are powerful at solving graph classification tasks, yet applied problems often contain noisy labels. In this work, we study GNN robustness to label noi…
Task Singular Vectors: Reducing Task Interference in Model Merging
Antonio Andrea Gargiulo, Donato Crisostomi, Maria Sofia Bucarelli +3
Task Arithmetic has emerged as a simple yet effective method to merge models without additional training. However, by treating entire networks as flat parameter vectors, it overloo…
ATM: Improving Model Merging by Alternating Tuning and Merging
Luca Zhou, Daniele Solombrino, Donato Crisostomi +3
Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In thi…
ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain
Guillermo Bernárdez, Lev Telyatnikov, Marco Montagna +70
This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learnin…
: Gradient-based and Task-Agnostic machine Unlearning
Daniel Trippa, Cesare Campagnano, Maria Sofia Bucarelli +2
Machine Unlearning, the process of selectively eliminating the influence of certain data examples used during a model's training, has gained significant attention as a means for pr…
Link Prediction with Physics-Inspired Graph Neural Networks
Andrea Giuseppe Di Francesco, Francesco Caso, Maria Sofia Bucarelli +1
The message-passing mechanism underlying Graph Neural Networks (GNNs) is not naturally suited for heterophilic datasets, where adjacent nodes often have different labels. Most solu…
A topological description of loss surfaces based on Betti Numbers
Maria Sofia Bucarelli, Giuseppe Alessio D'Inverno, Monica Bianchini +2
In the context of deep learning models, attention has recently been paid to studying the surface of the loss function in order to better understand training with methods based on g…
On Generalization Bounds for Projective Clustering
Maria Sofia Bucarelli, Matilde Fjeldsø Larsen, Chris Schwiegelshohn +1
Given a set of points, clustering consists of finding a partition of a point set into clusters such that the center to which a point is assigned is as close as possible. Most c…
Hypergraph Neural Networks through the Lens of Message Passing: A Common Perspective to Homophily and Architecture Design
Lev Telyatnikov, Maria Sofia Bucarelli, Guillermo Bernardez +3
Most of the current hypergraph learning methodologies and benchmarking datasets in the hypergraph realm are obtained by lifting procedures from their graph analogs, leading to over…
Learning with Noisy Labels through Learnable Weighting and Centroid Similarity
Farooq Ahmad Wani, Maria Sofia Bucarelli, Fabrizio Silvestri
We introduce a novel method for training machine learning models in the presence of noisy labels, which are prevalent in domains such as medical diagnosis and autonomous driving an…
NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks
Federico Siciliano, Maria Sofia Bucarelli, Gabriele Tolomei +1
In this work, we formulate NEWRON: a generalization of the McCulloch-Pitts neuron structure. This new framework aims to explore additional desirable properties of artificial neuron…