1,401 research outputs found
Deep Learning for Dynamic Graphs: Models and Benchmarks
No full textRecent progress in research on deep graph networks (DGNs) has led to a maturation of the domain of learning on graphs. Despite the growth of this research field, there are still important challenges that are yet unsolved. Specifically, there is an urge of making DGNs suitable for predictive tasks on real-world systems of interconnected entities, which evolve over time. With the aim of fostering research in the domain of dynamic graphs, first, we survey recent advantages in learning both temporal and spatial information, providing a comprehensive overview of the current state-of-the-art in the domain of representation learning for dynamic graphs. Second, we conduct a fair performance comparison among the most popular proposed approaches on node-and edge-level tasks, leveraging rigorous model selection and assessment for all the methods, thus establishing a sound baseline for evaluating new architectures and approaches
Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
No full textDeep Graph Networks (DGNs) currently dominate the research landscape of learning from graphs, due to their efficiency and ability to implement an adaptive message-passing scheme between the nodes. However, DGNs are typically limited in their ability to propagate and preserve long-term dependencies between nodes, \ie they suffer from the over-squashing phenomena. This reduces their effectiveness, since predictive problems may require to capture interactions at different, and possibly large, radii in order to be effectively solved. In this work, we present Anti-Symmetric Deep Graph Networks (A-DGNs), a framework for stable and non-dissipative DGN design, conceived through the lens of ordinary differential equations. We give theoretical proof that our method is stable and non-dissipative, leading to two key results: long-range information between nodes is preserved, and no gradient vanishing or explosion occurs in training. We empirically validate the proposed approach on several graph benchmarks, showing that A-DGN yields to improved performance and enables to learn effectively even when dozens of layers are used
Emotional dysregulation as trans-nosographic psychopathological dimension in adulthood: A systematic review
No full textINTRODUCTION: Emotional dysregulation (ED) is characterized by inappropriate emotional reactions related to environmental or cognitive stimuli. In most recent years, increasing interest has been devoted to its definition and detection across mental disorders for its detrimental role progressively highlighted in both neurodevelopment and adult mental disorders, with implications on the severity of clinical manifestations. The aim of this systematic review was to evaluate and gather the scientific evidence about ED in adult psychiatric population to elucidate the concept of ED as trans-nosographic entity. METHODS: The electronics databases PubMed, Scopus and Web of Science was reviewed to identify studies in accordance with the PRISMA guidelines; at the end of the selection process a total of 29 studies (N = 709; N = 658; N = 1,425) was included. All studies included assessed the presence of ED symptoms, by means of a validate scale in adult (>18 years of age), in clinically diagnosed patients as well as healthy control participants. RESULTS: Our results suggest ED as a trans-diagnostic factor across multiple mental disorders, such as bipolar disorder, attention deficit hyperactivity disorder, autism spectrum disorder, personality disorders; a better definition of this concept could be helpful to interpret and clarify many clinical cases and improve their diagnostic and therapeutic management
Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks
No full textThe dynamics of information diffusion within graphs is a critical open issue that heavily influences graph representation learning, especially when considering long-range propagation. This calls for principled approaches that control and regulate the degree of propagation and dissipation of information throughout the neural flow. Motivated by this, we introduce port-Hamiltonian Deep Graph Networks, a novel framework that models neural information flow in graphs by building on the laws of conservation of Hamiltonian dynamical systems. We reconcile under a single theoretical and practical framework both non-dissipative long-range propagation and non-conservative behaviors, introducing tools from mechanical systems to gauge the equilibrium between the two components. Our approach can be applied to general message-passing architectures, and it provides theoretical guarantees on information conservation in time. Empirical results prove the effectiveness of our port-Hamiltonian scheme in pushing simple graph convolutional architectures to state-of-the-art performance in long-range benchmarks
Hidden Markov Models for Temporal Graph Representation Learning
No full textWe propose the Hidden Markov Model for temporal Graphs,
a deep and fully probabilistic model for learning in the domain of dynamic
time-varying graphs. We extend hidden Markov models for sequences to
the graph domain by stacking probabilistic layers that perform efficient
message passing and learn representations for the individual nodes. We
evaluate the goodness of the learned representations on temporal node
prediction tasks, and we observe promising results compared to neural
approache
Temporal Graph ODEs for Irregularly-Sampled Time Series
No full textModern graph representation learning works mostly under the assumption of dealing with regularly sampled temporal graph snapshots, which is far from realistic, e.g., social networks and physical systems are characterized by continuous dynamics and sporadic observations. To address this limitation, we introduce the Temporal Graph Ordinary Differential Equation (TG-ODE) framework, which learns both the temporal and spatial dynamics from graph streams where the intervals between observations are not regularly spaced. We empirically validate the proposed approach on several graph benchmarks, showing that TG-ODE can achieve state-of-the-art performance in irregular graph stream tasks
Correction to: When terminology hinders research: the colloquialisms of transitions of control in automated driving (Cognition, Technology & Work, (2022), 10.1007/s10111-022-00705-3)
No full textIn the original article, author affiliation published with error. The correct affiliations are: Davide Maggi—Institute for Transport Studies, Leeds, UK. Richard Romano—Institute for Transport Studies, Leeds, UK. Oliver Carsten—Institute for Transport Studies, Leeds, UK. Joost C. F. De Winter—Faculty of Mechanical, Maritime and Materials Engineering, Delft University of Technology, Delft, The Netherlands. The original article has been corrected.Human-Robot Interactio
Admiel Kosman, Siamo giunti a Dio
No full textInternational audienceSix poems from Israeli poet Admiel Kosman translated from the Hebrew into Italian. Selection of poems, presentation of the author, translation and notes by Davide Mano
Admiel Kosman, Siamo giunti a Dio
No full textInternational audienceSix poems from Israeli poet Admiel Kosman translated from the Hebrew into Italian. Selection of poems, presentation of the author, translation and notes by Davide Mano
- …
