3 citations · 4 across the 7 of their papers we have counts for
7 papers
Aitchison Embeddings for Learning Compositional Graph Representations
Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas +2
Representation learning is central to graph machine learning, powering tasks such as link prediction and node classification. However, most graph embeddings are hard to interpret,…
Archetypal Graph Generative Models: Explainable and Identifiable Communities via Anchor-Dominant Convex Hulls
Nikolaos Nakis, Chrysoula Kosma, Panagiotis Promponas +2
Representation learning has been essential for graph machine learning tasks such as link prediction, community detection, and network visualization. Despite recent advances in achi…
The Signed Two-Space Proximity Model for Learning Representations in Protein-Protein Interaction Networks
Nikolaos Nakis, Chrysoula Kosma, Anastasia Brativnyk +3
Accurately predicting complex protein-protein interactions (PPIs) is crucial for decoding biological processes, from cellular functioning to disease mechanisms. However, experiment…
Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings
Nikolaos Nakis, Chrysoula Kosma, Giannis Nikolentzos +3
Autoencoders based on Graph Neural Networks (GNNs) have garnered significant attention in recent years for their ability to extract informative latent representations, characterizi…
Time-Parameterized Convolutional Neural Networks for Irregularly Sampled Time Series
Chrysoula Kosma, Giannis Nikolentzos, Michalis Vazirgiannis
Irregularly sampled multivariate time series are ubiquitous in several application domains, leading to sparse, not fully-observed and non-aligned observations across different vari…
TimeGNN: Temporal Dynamic Graph Learning for Time Series Forecasting
Nancy Xu, Chrysoula Kosma, Michalis Vazirgiannis
Time series forecasting lies at the core of important real-world applications in many fields of science and engineering. The abundance of large time series datasets that consist of…
Time Series Forecasting Models Copy the Past: How to Mitigate
Chrysoula Kosma, Giannis Nikolentzos, Nancy Xu +1
Time series forecasting is at the core of important application domains posing significant challenges to machine learning algorithms. Recently neural network architectures have bee…