Search Results for author:
Found 29 papers, 12 papers with code
IFH: a Diffusion Framework for Flexible Design of Graph Generative Models
An insertion process learns to reverse this removal process by inserting arcs and nodes according to the specified sequentiality degree.
Assessing the Emergent Symbolic Reasoning Abilities of Llama Large Language Models
Large Language Models (LLMs) achieve impressive performance in a wide range of tasks, even if they are often trained with the only objective of chatting fluently with users.
Benchmarking GPT-4 on Algorithmic Problems: A Systematic Evaluation of Prompting Strategies
Large Language Models (LLMs) have revolutionized the field of Natural Language Processing thanks to their ability to reuse knowledge acquired on massive text corpora on a wide variety of downstream tasks, with minimal (if any) tuning steps.
A Neural Rewriting System to Solve Algorithmic Problems
In this work, we focus on formula simplification problems, a class of synthetic benchmarks used to study the systematic generalization capabilities of neural architectures.
A Hybrid System for Systematic Generalization in Simple Arithmetic Problems
Solving symbolic reasoning problems that require compositionality and systematicity is considered one of the key ingredients of human intelligence.
RGCVAE: Relational Graph Conditioned Variational Autoencoder for Molecule Design
Identifying molecules that exhibit some pre-specified properties is a difficult problem to solve.
Weakly-Supervised Visual-Textual Grounding with Semantic Prior Refinement
The first untrained module aims to return a rough alignment between textual phrases and bounding boxes.
A Better Loss for Visual-Textual Grounding
Given a textual phrase and an image, the visual grounding problem is the task of locating the content of the image referenced by the sentence.
Simple Graph Convolutional Networks
Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago.
Conditional Variational Capsule Network for Open Set Recognition
In this way, we are able to control the compactness of the features of the same class around the center of the gaussians, thus controlling the ability of the classifier in detecting samples from unknown classes.
Polynomial Graph Convolutional Networks
In this paper, we propose a different strategy, considering a single graph convolution layer that independently exploits neighbouring nodes at different topological distances, generating decoupled representations for each of them.
Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization
Training RNNs to learn long-term dependencies is difficult due to vanishing gradients.
Conditional Constrained Graph Variational Autoencoders for Molecule Design
In recent years, deep generative models for graphs have been used to generate new molecules.
A Systematic Assessment of Deep Learning Models for Molecule Generation
In recent years the scientific community has devoted much effort in the development of deep learning models for the generation of new molecules with desirable properties (i. e. drugs).
Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory
The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales.
Encoding-based Memory Modules for Recurrent Neural Networks
The experimental results on synthetic and real-world datasets show that specializing the training algorithm to train the memorization component always improves the final performance whenever the memorization of long sequences is necessary to solve the problem.
Autoencoder-based Initialization for Recurrent Neural Networks with a Linear Memory
We propose an initialization schema that sets the weights of a recurrent architecture to approximate a linear autoencoder of the input sequences, which can be found with a closed-form solution.
Embeddings and Representation Learning for Structured Data
Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form.
On Filter Size in Graph Convolutional Networks
Recently, many researchers have been focusing on the definition of neural networks for graphs.
Pre-training Graph Neural Networks with Kernels
Many machine learning techniques have been proposed in the last few years to process data represented in graph-structured form.
Linear Memory Networks
By building on such conceptualization, we introduce the Linear Memory Network, a recurrent model comprising a feedforward neural network, realizing the non-linear functional transformation, and a linear autoencoder for sequences, implementing the memory component.
LSTM Networks for Data-Aware Remaining Time Prediction of Business Process Instances
Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints.
Time and Activity Sequence Prediction of Business Process Instances
However, in real cases this assumption is not always true.
Graph Kernels exploiting Weisfeiler-Lehman Graph Isomorphism Test Extensions
In this paper we present a novel graph kernel framework inspired the by the Weisfeiler-Lehman (WL) isomorphism tests.
A tree-based kernel for graphs with continuous attributes
While existing kernel methods are effective techniques for dealing with graphs having discrete node labels, their adaptation to non-discrete or continuous node attributes has been limited, mainly for computational issues.
Ordered Decompositional DAG Kernels Enhancements
In this paper, we show how the Ordered Decomposition DAGs (ODD) kernel framework, a framework that allows the definition of graph kernels from tree kernels, allows to easily define new state-of-the-art graph kernels.
An Empirical Study on Budget-Aware Online Kernel Algorithms for Streams of Graphs
It turns out that, when strict memory budget constraints have to be enforced, working in feature space, given the current state of the art on graph kernels, is more than a viable alternative to dual approaches, both in terms of speed and classification performance.
Extending local features with contextual information in graph kernels
Different kernels consider different types of substructures.
Pre-training of Recurrent Neural Networks via Linear Autoencoders
We propose a pre-training technique for recurrent neural networks based on linear autoencoder networks for sequences, i. e. linear dynamical systems modelling the target sequences.
