Search Results for author:
Found 59 papers, 22 papers with code
Task Singular Vectors: Reducing Task Interference in Model Merging
In this paper, we study task vectors at the layer level, focusing on task layer matrices and their singular value decomposition.
STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing
Spatio-Temporal predictive Learning is a self-supervised learning paradigm that enables models to identify spatial and temporal patterns by predicting future frames based on past frames.
A Theoretical Analysis of Recommendation Loss Functions under Negative Sampling
We show that the BPR bound on NDCG is weaker than that of BCE, contradicting the common assumption that BPR is superior to BCE in RSs training.
ATM: Improving Model Merging by Alternating Tuning and Merging
Building on this insight, we propose viewing model merging as a single step in an iterative process that Alternates between Tuning and Merging (ATM).
Beyond position: how rotary embeddings shape representations and memory in autoregressive transfomers
Rotary Positional Embeddings (RoPE) enhance positional encoding in Transformer models, yet their full impact on model dynamics remains underexplored.
Eco-Aware Graph Neural Networks for Sustainable Recommendations
Recommender systems play a crucial role in alleviating information overload by providing personalized recommendations tailored to users' preferences and interests.
Natural Language Counterfactual Explanations for Graphs Using Large Language Models
Explainable Artificial Intelligence (XAI) has emerged as a critical area of research to unravel the opaque inner logic of (deep) machine learning models.
A Reproducible Analysis of Sequential Recommender Systems
By leveraging sequential data, SRSs can identify temporal patterns in user behaviour, significantly improving recommendation accuracy and relevance. Ensuring the reproducibility of these models is paramount for advancing research and facilitating comparisons between them.
A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems
Retrieval Augmented Generation (RAG) represents a significant advancement in artificial intelligence combining a retrieval phase with a generative phase, with the latter typically being powered by large language models (LLMs).
Predicting Award Winning Research Papers at Publication Time
We made our experiments considering the ArnetMiner citation graph, while the ground truth on award-winning papers has been obtained from a collection of best paper awards from 32 computer science conferences.
Graph Neural Re-Ranking via Corpus Graph
Re-ranking systems aim to reorder an initial list of documents to satisfy better the information needs associated with a user-provided query.
Generating Query Recommendations via LLMs
We then improved our system by proposing a version that exploits query logs called Retriever-Augmented GQR (RA-GQR).
Debiasing Machine Unlearning with Counterfactual Examples
This bias emerges from two main sources: (1) data-level bias, characterized by uneven data removal, and (2) algorithm-level bias, which leads to the contamination of the remaining dataset, thereby degrading model accuracy.
$\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning
In this study, we introduce Gradient-based and Task-Agnostic machine Unlearning ($\nabla \tau$), an optimization framework designed to remove the influence of a subset of training data efficiently.
Variational Inference of Parameters in Opinion Dynamics Models
We validate our method on a bounded confidence model with agent roles (leaders and followers).
Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks
While promising, this move presents significant challenges for personalized recommendations.
Link Prediction under Heterophily: A Physics-Inspired Graph Neural Network Approach
Physics-Inspired GNNs such as GRAFF provided a significant contribution to enhance node classification performance under heterophily, thanks to the adoption of physics biases in the message-passing.
The Power of Noise: Redefining Retrieval for RAG Systems
Retrieval-Augmented Generation (RAG) has recently emerged as a method to extend beyond the pre-trained knowledge of Large Language Models by augmenting the original prompt with relevant passages or documents retrieved by an Information Retrieval (IR) system.
A topological description of loss surfaces based on Betti Numbers
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 gradient descent.
A graph neural network-based model with Out-of-Distribution Robustness for enhancing Antiretroviral Therapy Outcome Prediction for HIV-1
We evaluated these models' robustness against Out-of-Distribution drugs in the test set, with a specific focus on the GNN's role in handling such scenarios.
Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It
Fake news detection models are critical to countering disinformation but can be manipulated through adversarial attacks.
Enhancing Content Moderation with Culturally-Aware Models
Our findings reinforce the need for an adaptable content moderation approach that remains flexible in response to the diverse cultural landscapes it operates in and represents a step towards a more equitable and culturally sensitive framework for content moderation, demonstrating what is achievable in this domain.
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.
Prompt-to-OS (P2OS): Revolutionizing Operating Systems and Human-Computer Interaction with Integrated AI Generative Models
In this paper, we present a groundbreaking paradigm for human-computer interaction that revolutionizes the traditional notion of an operating system.
Investigating the Robustness of Sequential Recommender Systems Against Training Data Perturbations
However, their robustness in the face of perturbations in training data remains a largely understudied yet critical issue.
RRAML: Reinforced Retrieval Augmented Machine Learning
The emergence of large language models (LLMs) has revolutionized machine learning and related fields, showcasing remarkable abilities in comprehending, generating, and manipulating human language.
Fauno: The Italian Large Language Model that will leave you senza parole!
This paper presents Fauno, the first and largest open-source Italian conversational Large Language Model (LLM).
Renormalized Graph Neural Networks
It is recognized as the preferred lens through which to study complex systems, offering a framework that can untangle their intricate dynamics.
Integrating Item Relevance in Training Loss for Sequential Recommender Systems
Sequential Recommender Systems (SRSs) are a popular type of recommender system that learns from a user's history to predict the next item they are likely to interact with.
Multimodal Neural Databases
The rise in loosely-structured data available through text, images, and other modalities has called for new ways of querying them.
The Dark Side of Explanations: Poisoning Recommender Systems with Counterfactual Examples
By reversing the learning process of the recommendation model, we thus develop a proficient greedy algorithm to generate fabricated user profiles and their associated interaction records for the aforementioned surrogate model.
Sheaf4Rec: Sheaf Neural Networks for Graph-based Recommender Systems
GNNs have proven to be effective in addressing the challenges posed by recommendation systems by efficiently modeling graphs in which nodes represent users or items and edges denote preference relationships.
Learning with Noisy Labels through Learnable Weighting and Centroid Similarity
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 and have the potential to degrade a model's generalization performance.
Attention-likelihood relationship in transformers
We analyze how large language models (LLMs) represent out-of-context words, investigating their reliance on the given context to capture their semantics.
Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels
In practical settings, classification datasets are obtained through a labelling process that is usually done by humans.
Sparse Vicious Attacks on Graph Neural Networks
In this work, we focus on a specific, white-box attack to GNN-based link prediction models, where a malicious node aims to appear in the list of recommended nodes for a given target victim.
GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations
Although powerful, it is very difficult for a GNN-based recommender system to attach tangible explanations of why a specific item ends up in the list of suggestions for a given user.
Encoding Concepts in Graph Neural Networks
The opaque reasoning of Graph Neural Networks induces a lack of human trust.
Detecting and Understanding Harmful Memes: A Survey
One interesting finding is that many types of harmful memes are not really studied, e. g., such featuring self-harm and extremism, partly due to the lack of suitable datasets.
ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models
However, existing CF generation methods either exploit the internals of specific models or depend on each sample's neighborhood, thus they are hard to generalize for complex models and inefficient for large datasets.
NEWRON: A New Generalization of the Artificial Neuron to Enhance the Interpretability of Neural Networks
In this work, we formulate NEWRON: a generalization of the McCulloch-Pitts neuron structure.
Detecting Propaganda Techniques in Memes
We further create and release a new corpus of 950 memes, carefully annotated with 22 propaganda techniques, which can appear in the text, in the image, or in both.
Database Reasoning Over Text
Neural models have shown impressive performance gains in answering queries from natural language text.
SemEval-2021 Task 6: Detection of Persuasion Techniques in Texts and Images
We describe SemEval-2021 task 6 on Detection of Persuasion Techniques in Texts and Images: the data, the annotation guidelines, the evaluation setup, the results, and the participating systems.
CycleDRUMS: Automatic Drum Arrangement For Bass Lines Using CycleGAN
The two main research threads in computer-based music generation are: the construction of autonomous music-making systems, and the design of computer-based environments to assist musicians.
A Survey on Multimodal Disinformation Detection
As a result, researchers started leveraging different modalities and combinations thereof to tackle online multimodal offensive content.
CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks
In this work, we propose a method for generating CF explanations for GNNs: the minimal perturbation to the input (graph) data such that the prediction changes.
Automatic Music Production Using Generative Adversarial Networks
In this work, we propose a novel framework for $\textit{automatic music arrangement from raw audio in the frequency domain}$.
Neural Databases
We describe NeuralDB, a database system with no pre-defined schema, in which updates and queries are given in natural language.
Preserving Integrity in Online Social Networks
Online social networks provide a platform for sharing information and free expression.
Concept Matching for Low-Resource Classification
We propose a model to tackle classification tasks in the presence of very little training data.
Node Masking: Making Graph Neural Networks Generalize and Scale Better
Graph Neural Networks (GNNs) have received a lot of interest in the recent times.
How Decoding Strategies Affect the Verifiability of Generated Text
A generated sentence is verifiable if it can be corroborated or disproved by Wikipedia, and we find that the verifiability of generated text strongly depends on the decoding strategy.
Soft Token Matching for Interpretable Low-Resource Classification
We propose a model to tackle classification tasks in the presence of very little training data.
Misspelling Oblivious Word Embeddings
In this paper we present a method to learn word embeddings that are resilient to misspellings.
Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking
There are many circumstances however where it is important to understand (i) why a model outputs a certain prediction on a given instance, (ii) which adjustable features of that instance should be modified, and finally (iii) how to alter such a prediction when the mutated instance is input back to the model.
Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising
For this reason search engines often provide a service of advanced matching, which automatically finds additional relevant queries for advertisers to bid on.
Neighborhood Sensitive Mapping for Zero-Shot Classification using Independently Learned Semantic Embeddings
In a traditional setting, classifiers are trained to approximate a target function $f:X \rightarrow Y$ where at least a sample for each $y \in Y$ is presented to the training algorithm.
