Search Results for author:
Found 11 papers, 8 papers with code
Visualisation Methods for Diachronic Semantic Shift
We develop three visualisation methods that can show, given a root word: the temporal change in its linguistic context, word re-occurrence, degree of similarity, time continuity, and separate trends per publisher location.
Learning the mechanisms of network growth
We propose a novel model-selection method for dynamic real-life networks.
Ranked #1 on
Graph Classification
on Synthetic Dynamic Networks
Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations
With these novelties, we show the following: (a) The proposed MGE allows to extract topological metrics that are much better predictors of the accuracy drop than metrics computed from current input-agnostic BGEs; (b) Which metrics are important at different sparsity levels and for different architectures; (c) A mixture of our topological metrics can rank PaI algorithms more effectively than Ramanujan-based metrics.
Large-scale multi-objective influence maximisation with network downscaling
Finding the most influential nodes in a network is a computationally hard problem with several possible applications in various kinds of network-based problems.
Automated fault tree learning from continuous-valued sensor data: a case study on domestic heaters
We obtain fault trees for the 11 failure variables, and evaluate them in two ways: quantitatively, with a significance score, and qualitatively, with domain specialists.
Bias in Automated Image Colorization: Metrics and Error Types
We measure the color shifts present in colorized images from the ADE20K dataset, when colorized by the automatic GAN-based DeOldify model.
Look back, look around: a systematic analysis of effective predictors for new outlinks in focused Web crawling
In the literature, many feature designs have been proposed for predicting changes in the Web.
The network signature of constellation line figures
We then form the network of constellations (as linked by their similarity), to study how similar cultures are by computing their assortativity (or homophily) over the network.
Independent Prototype Propagation for Zero-Shot Compositionality
Next we propagate the independent prototypes through a compositional graph, to learn compositional prototypes of novel attribute-object combinations that reflect the dependencies of the target distribution.
Top influencers can be identified universally by combining classical centralities
Information flow, opinion, and epidemics spread over structured networks.
Causal Discovery with Attention-Based Convolutional Neural Networks
We therefore present the Temporal Causal Discovery Framework (TCDF), a deep learning framework that learns a causal graph structure by discovering causal relationships in observational time series data.
