20 citations · 40 across the 12 of their papers we have counts for
12 papers
FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding
Theodoros Aivalis, Iraklis A. Klampanos, Antonis Troumpoukis +1
The rapid deployment of generative AI has amplified the critical need for Training Data Attribution to ensure transparency and accountability. However, current parametric approache…
Peek2: Regex-free Byte-level Byte-Pair Encoding Pretokenizer for LLM Inference on Edge Devices
Liu Zai, Iraklis Klampanos
Pretokenization is a crucial, sequential pass in Byte-level BPE tokenizers, yet little work has been done to optimize it for edge-side inference. Our proposed new implementation, P…
Training Data Attribution for Image Generation using Ontology-Aligned Knowledge Graphs
Theodoros Aivalis, Iraklis A. Klampanos, Antonis Troumpoukis +1
As generative models become powerful, concerns around transparency, accountability, and copyright violations have intensified. Understanding how specific training data contributes…
Enhancing Interpretability in Generative AI Through Search-Based Data Influence Analysis
Theodoros Aivalis, Iraklis A. Klampanos, Antonis Troumpoukis +1
Generative AI models offer powerful capabilities but often lack transparency, making it difficult to interpret their output. This is critical in cases involving artistic or copyrig…
WeLa-VAE: Learning Alternative Disentangled Representations Using Weak Labels
Vasilis Margonis, Athanasios Davvetas, Iraklis A. Klampanos
Learning disentangled representations without supervision or inductive biases, often leads to non-interpretable or undesirable representations. On the other hand, strict supervisio…
Unsupervised Severe Weather Detection Via Joint Representation Learning Over Textual and Weather Data
Athanasios Davvetas, Iraklis A. Klampanos
When observing a phenomenon, severe cases or anomalies are often characterised by deviation from the expected data distribution. However, non-deviating data samples may also implic…
Learning Improved Representations by Transferring Incomplete Evidence Across Heterogeneous Tasks
Athanasios Davvetas, Iraklis A. Klampanos
Acquiring ground truth labels for unlabelled data can be a costly procedure, since it often requires manual labour that is error-prone. Consequently, the available amount of labell…
Evidence Transfer for Improving Clustering Tasks Using External Categorical Evidence
Athanasios Davvetas, Iraklis A. Klampanos, Vangelis Karkaletsis
In this paper we introduce evidence transfer for clustering, a deep learning method that can incrementally manipulate the latent representations of an autoencoder, according to ext…
ANNETT-O: An Ontology for Describing Artificial Neural Network Evaluation, Topology and Training
Iraklis A. Klampanos, Athanasios Davvetas, Antonis Koukourikos +1
Deep learning models, while effective and versatile, are becoming increasingly complex, often including multiple overlapping networks of arbitrary depths, multiple objectives and n…
Autoencoder-Driven Weather Clustering for Source Estimation during Nuclear Events
I. A. Klampanos, A. Davvetas, S. Andronopoulos +3
Emergency response applications for nuclear or radiological events can be significantly improved via deep feature learning due to the hidden complexity of the data and models invol…
The Design of a Community Science Cloud: The Open Science Data Cloud Perspective
Robert L. Grossman, Matthew Greenway, Allison P. Heath +9
In this paper we describe the design, and implementation of the Open Science Data Cloud, or OSDC. The goal of the OSDC is to provide petabyte-scale data cloud infrastructure and re…
VERCE delivers a productive e-Science environment for seismology research
Malcolm Atkinson, Michele Carpené, Emanuele Casarotti +18
The VERCE project has pioneered an e-Infrastructure to support researchers using established simulation codes on high-performance computers in conjunction with multiple sources of…