46 citations · 71 across the 12 of their papers we have counts for
14 papers
Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
Andreas Pattichis, Constantine Dovrolis
LLMs are trained once, then deployed into a world that never stops changing. External memory compensates for this, but most systems manage it explicitly rather than letting it adap…
Gradual Capacity Growth for Sparse Network Discovery
Qihang Yao, Constantine Dovrolis
Sparse neural network methods typically assume that the target sparsity (or density) is fixed in advance, even though the relationship between network capacity and performance is g…
PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similarity
Mustafa Burak Gurbuz, Xingyu Zheng, Constantine Dovrolis
As deep learning continues to be driven by ever-larger datasets, understanding which examples are most important for generalization has become a critical question. While progress i…
Patch-Based Contrastive Learning and Memory Consolidation for Online Unsupervised Continual Learning
Cameron Taylor, Vassilis Vassiliades, Constantine Dovrolis
We focus on a relatively unexplored learning paradigm known as {\em Online Unsupervised Continual Learning} (O-UCL), where an agent receives a non-stationary, unlabeled data stream…
SHARP: Sparsity and Hidden Activation RePlay for Neuro-Inspired Continual Learning
Mustafa Burak Gurbuz, Jean Michael Moorman, Constantine Dovrolis
Deep neural networks (DNNs) struggle to learn in dynamic environments since they rely on fixed datasets or stationary environments. Continual learning (CL) aims to address this lim…
Unsupervised Progressive Learning and the STAM Architecture
James Smith, Cameron Taylor, Seth Baer +1
We first pose the Unsupervised Progressive Learning (UPL) problem: an online representation learning problem in which the learner observes a non-stationary and unlabeled data strea…
Nash-Peering: A New Techno-Economic Framework for Internet Interconnections
Doron Zarchy, Amogh Dhamdhere, Constantine Dovrolis +1
The current framework of Internet interconnections, based on transit and settlement-free peering relations, has systemic problems that often cause peering disputes. We propose a ne…
The Hourglass Effect in Hierarchical Dependency Networks
Kaeser M Sabrin, Constantine Dovrolis
Many hierarchically modular systems are structured in a way that resembles an hourglass. This "hourglass effect" means that the system generates many outputs from many inputs throu…
δ-MAPS: From spatio-temporal data to a weighted and lagged network between functional domains
Ilias Fountalis, Annalisa Bracco, Bistra Dilkina +2
We propose δ-MAPS, a method that analyzes spatio-temporal data to first identify the distinct spatial components of the underlying system, referred to as "domains", and second to i…
Lexis: An Optimization Framework for Discovering the Hierarchical Structure of Sequential Data
Payam Siyari, Bistra Dilkina, Constantine Dovrolis
Data represented as strings abounds in biology, linguistics, document mining, web search and many other fields. Such data often have a hierarchical structure, either because they w…
A symmetry-based method to infer structural brain networks from tractography data
Kamal Shadi, Saideh Bakhshi, David A. Gutman +2
Recent progress in diffusion MRI and tractography algorithms as well as the launch of the Human Connectome Project (HCP) have provided brain research with an abundance of structura…
Co-evolutionary dynamics in social networks: A case study of Twitter
Demetris Antoniades, Constantine Dovrolis
Complex networks often exhibit co-evolutionary dynamics, meaning that the network topology and the state of nodes or links are coupled, affecting each other in overlapping time sca…
An explanatory evo-devo model for the developmental hourglass
Saamer Akhshabi, Shrutii Sarda, Constantine Dovrolis +1
The "developmental hourglass" describes a pattern of increasing morphological divergence towards earlier and later embryonic development, separated by a period of significant conse…
Can User-Level Probing Detect and Diagnose Common Home-WLAN Pathologies?
Partha Kanuparthy, Constantine Dovrolis, Konstantina Papagiannaki +2
Common WLAN pathologies include low signal-to-noise ratio, congestion, hidden terminals or interference from non-802.11 devices and phenomena. Prior work has focused on the detecti…