5 citations · 11 across the 3 of their papers we have counts for
7 papers
Jointly Learnable Data Augmentations for Self-Supervised GNNs
Zekarias T. Kefato, Sarunas Girdzijauskas, Hannes Stärk
Self-supervised Learning (SSL) aims at learning representations of objects without relying on manual labeling. Recently, a number of SSL methods for graph representation learning h…
Self-supervised Graph Neural Networks without explicit negative sampling
Zekarias T. Kefato, Sarunas Girdzijauskas
Real world data is mostly unlabeled or only few instances are labeled. Manually labeling data is a very expensive and daunting task. This calls for unsupervised learning techniques…
Dynamic Embeddings for Interaction Prediction
Zekarias T. Kefato, Sarunas Girdzijauskas, Nasrullah Sheikh +1
In recommender systems (RSs), predicting the next item that a user interacts with is critical for user retention. While the last decade has seen an explosion of RSs aimed at identi…
Pedestrian Trajectory Prediction with Convolutional Neural Networks
Simone Zamboni, Zekarias Tilahun Kefato, Sarunas Girdzijauskas +2
Predicting the future trajectories of pedestrians is a challenging problem that has a range of application, from crowd surveillance to autonomous driving. In literature, methods to…
Gossip and Attend: Context-Sensitive Graph Representation Learning
Zekarias T. Kefato, Sarunas Girdzijauskas
Graph representation learning (GRL) is a powerful technique for learning low-dimensional vector representation of high-dimensional and often sparse graphs. Most studies explore the…
Which way? Direction-Aware Attributed Graph Embedding
Zekarias T. Kefato, Nasrullah Sheikh, Alberto Montresor
Graph embedding algorithms are used to efficiently represent (encode) a graph in a low-dimensional continuous vector space that preserves the most important properties of the graph…