Neural Networks and Support Vector Machines

Self-Supervised Learning, JEPA, World Models, and AI’s future

Abstract

Current AI architectures remain significantly inferior to humans and animals in their ability to reason, plan, and understand the physical world. This lecture unpacks the rationale for moving beyond supervised and reinforcement learning toward objective-...
Feature selection in linear support vector machines via a hard cardinality constraint: A scalable conic decomposition approach

In this paper, we study the embedded feature selection problem in linear Support Vector Machines (SVMs), in which a cardinality constraint is employed, leading to an interpretable classification model. The problem is NP-hard due to the presence of the cardinality constraint, even though the...
Convergence of ease-controlled Random Reshuffling gradient Algorithms under Lipschitz smoothness

In this work, we consider minimizing the average of a very large number of smooth and possibly non-convex functions, and we focus on two widely used minibatch frameworks to tackle this optimization problem: Incremental Gradient (IG) and Random Reshuffling (RR). We define ease-controlled...
Parallelizing GPU-based Mini-Batch Graph Neural Network Training

Abstract: Many datasets are best represented as graphs of entities connected by relationships rather than as a single uniform dataset or table. Graph Neural Networks (GNNs) have been used to...
Seminario pubblico di Federica Baccini (Procedura valutativa per n.1 posto di Ricercatore a tempo determinato tipologia A - SC 09/H1 SSD ING-INF/05)

Speaker: Federica Baccini

When: 10 Luglio 2023

Where: Aula Magna - DIAG

Title: Analysis of multiple relations in multilayer and higher-order networks

Abstract: This seminar focuses on the extension of...
Integrating Graph Representation Learning and Diffusion: Computational Models and Applications in Chemistry and Medicine.

Title: Integrating Graph Representation Learning and Diffusion: Computational Models and Applications in Chemistry and Medicine.

Abstract

The talk will focus on recent methodological novelties and challenges in graph...
Theory of Deep Learning

The RSTLess research group is a dynamic and innovative team of researchers from Sapienza University of Rome, led by Professor Fabrizio Silvestri.

Our focus is on the cutting-edge fields of Deep Learning, Information Retrieval, Graph Neural Networks, and Natural Language Processing, with a...
NIAPU: Network-Informed Adaptive Positive-Unlabeled learning for disease gene identification

Motivation: Gene-disease associations are fundamental for understanding disease etiology and developing effective interventions and treatments. Identifying genes not yet associated with a disease due to a lack of studies is a challenging task in which prioritization based on prior knowledge is an...
EdgeSHAPer: Bond-Centric Shapley Value-Based Explanation Method for Graph Neural Networks

Graph neural networks (GNNs) recursively propagate signals along the edges of an input graph, integrate node feature information with graph structure, and learn object representations. Like other deep neural network models, GNNs have notorious black box character. For GNNs, only few approaches are...
Protocol to explain graph neural network predictions using an edge-centric Shapley value-based approach

Here we present EdgeSHAPer, a workflow for explaining graph neural networks by approximating Shapley values using Monte Carlo sampling. In this protocol, we describe steps to execute Python scripts for a chemical dataset from the original publication; however, this approach is also applicable to...