Search Results for author: Sarunas Girdzijauskas

Found 16 papers, 11 papers with code

Decentralized Word2Vec Using Gossip Learning

no code implementations NoDaLiDa 2021 Abdul Aziz Alkathiri, Lodovico Giaretta, Sarunas Girdzijauskas, Magnus Sahlgren

Advanced NLP models require huge amounts of data from various domains to produce high-quality representations.

Challenging the Assumption of Structure-based embeddings in Few- and Zero-shot Knowledge Graph Completion

1 code implementation LREC 2022 Filip Cornell, Chenda Zhang, Jussi Karlgren, Sarunas Girdzijauskas

In this paper, we report experiments on Few- and Zero-shot Knowledge Graph completion, where the objective is to add missing relational links between entities into an existing Knowledge Graph with few or no previous examples of the relation in question.

Descriptive Knowledge Graph Completion +1

Are We Wasting Time? A Fast, Accurate Performance Evaluation Framework for Knowledge Graph Link Predictors

no code implementations25 Jan 2024 Filip Cornell, Yifei Jin, Jussi Karlgren, Sarunas Girdzijauskas

First, we empirically find and theoretically motivate why sampling uniformly at random vastly overestimates the ranking performance of a method.

Learning Cellular Coverage from Real Network Configurations using GNNs

1 code implementation20 Apr 2023 Yifei Jin, Marios Daoutis, Sarunas Girdzijauskas, Aristides Gionis

Cellular coverage quality estimation has been a critical task for self-organized networks.

Open World Learning Graph Convolution for Latency Estimation in Routing Networks

1 code implementation8 Jul 2022 Yifei Jin, Marios Daoutis, Sarunas Girdzijauskas, Aristides Gionis

Accurate routing network status estimation is a key component in Software Defined Networking.

Decentralized adaptive clustering of deep nets is beneficial for client collaboration

1 code implementation17 Jun 2022 Edvin Listo Zec, Ebba Ekblom, Martin Willbo, Olof Mogren, Sarunas Girdzijauskas

We study the problem of training personalized deep learning models in a decentralized peer-to-peer setting, focusing on the setting where data distributions differ between the clients and where different clients have different local learning tasks.


Meta-Reinforcement Learning via Buffering Graph Signatures for Live Video Streaming Events

1 code implementation3 Oct 2021 Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas

By considering a new event as a task, we design an actor-critic learning scheme to compute the optimal policy on estimating the viewers' high-bandwidth connections.

Meta-Learning Meta Reinforcement Learning +2

Jointly Learnable Data Augmentations for Self-Supervised GNNs

1 code implementation23 Aug 2021 Zekarias T. Kefato, Sarunas Girdzijauskas, Hannes Stärk

Recently, a number of SSL methods for graph representation learning have achieved performance comparable to SOTA semi-supervised GNNs.

Data Augmentation Graph Representation Learning +2

A Deep Graph Reinforcement Learning Model for Improving User Experience in Live Video Streaming

no code implementations28 Jul 2021 Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas

We first formulate the user experience prediction problem as a classification task, accounting for the fact that most of the viewers at the beginning of an event have poor quality of experience due to low-bandwidth connections and limited interactions with the tracker.

Reinforcement Learning (RL)

Federated Word2Vec: Leveraging Federated Learning to Encourage Collaborative Representation Learning

no code implementations19 Apr 2021 Daniel Garcia Bernal, Lodovico Giaretta, Sarunas Girdzijauskas, Magnus Sahlgren

The results show that neither the quality of the results nor the convergence time in Federated Word2Vec deteriorates as compared to centralised Word2Vec.

Federated Learning Representation Learning

Self-supervised Graph Neural Networks without explicit negative sampling

2 code implementations27 Mar 2021 Zekarias T. Kefato, Sarunas Girdzijauskas

This calls for unsupervised learning techniques that are powerful enough to achieve comparable results as semi-supervised/supervised techniques.

Contrastive Learning Data Augmentation +1

Dynamic Embeddings for Interaction Prediction

1 code implementation10 Nov 2020 Zekarias T. Kefato, Sarunas Girdzijauskas, Nasrullah Sheikh, Alberto Montresor

In recommender systems (RSs), predicting the next item that a user interacts with is critical for user retention.

Recommendation Systems

Pedestrian Trajectory Prediction with Convolutional Neural Networks

no code implementations12 Oct 2020 Simone Zamboni, Zekarias Tilahun Kefato, Sarunas Girdzijauskas, Noren Christoffer, Laura Dal Col

In this work, we propose a new approach to pedestrian trajectory prediction, with the introduction of a novel 2D convolutional model.

Autonomous Driving Data Augmentation +2

Gossip and Attend: Context-Sensitive Graph Representation Learning

1 code implementation30 Mar 2020 Zekarias T. Kefato, Sarunas Girdzijauskas

In this study we show that in-order to extract high-quality context-sensitive node representations it is not needed to rely on supplementary node features, nor to employ computationally heavy and complex models.

Clustering Community Detection +3

Graph Neighborhood Attentive Pooling

1 code implementation28 Jan 2020 Zekarias T. Kefato, Sarunas Girdzijauskas

Network representation learning (NRL) is a powerful technique for learning low-dimensional vector representation of high-dimensional and sparse graphs.

Clustering Community Detection +3

Cannot find the paper you are looking for? You can Submit a new open access paper.