Yulia R. Gel — accepted AI-conference papers

2025

Fusing Multimodality of Large Language Models and Satellite Imagery via Simplicial Contrastive Learning for Latent Urban Feature Identification and Environmental Application

Yuzhou Chen, Jiue-An Yang, Hugo Kyo Lee, Calvin P. Tribby, Tarik Benmarhnia, Marta M. Jankowska +1

ICASSP 2025accepted

Satellite imagery is a readily available data source for monitoring a broad range of urban geographical contexts related to environmental, socio-demographic, and health disparities. To analyze satellite images, deep learning (DL) tools efficiently extract latent multi-dimensional characteristics, be…

Cited by 0 Source ↗Scholar ↗

2025

Topology-Informed Pre-training of Graph Neural Networks

Peiyu Liang, Yulia R. Gel, Yuzhou Chen

ICASSP 2025accepted

Pre-training has emerged as a dominant paradigm in graph representation learning to address data scarcity and generalization challenges. The majority of existing methods primarily focus on refining fine-tuning and prompting techniques to extract information from pre-trained models. However, the effe…

Cited by 0 Source ↗Scholar ↗

2024

SNN-PDE: Learning Dynamic PDEs from Data with Simplicial Neural Networks

Jae Choi, Yuzhou Chen, Huikyo Lee, Hyun Kim, Yulia R. Gel

AAAI 2024technical

Dynamics of many complex systems, from weather and climate to spread of infectious diseases, can be described by partial differential equations (PDEs). Such PDEs involve unknown function(s), partial derivatives, and typically multiple independent variables. The traditional numerical methods for sol…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

Time-Aware Knowledge Representations of Dynamic Objects with Multidimensional Persistence

Baris Coskunuzer, Ignacio Segovia-Dominguez, Yuzhou Chen, Yulia R. Gel

AAAI 2024technical

Learning time-evolving objects such as multivariate time series and dynamic networks requires the development of novel knowledge representation mechanisms and neural network architectures, which allow for capturing implicit time-dependent information contained in the data. Such information is typica…

Cited by 4 Source ↗PDF ↗Scholar ↗

2024

TopoGCL: Topological Graph Contrastive Learning

Yuzhou Chen, Jose Frias, Yulia R. Gel

AAAI 2024technical

Graph contrastive learning (GCL) has recently emerged as a new concept which allows for capitalizing on the strengths of graph neural networks (GNNs) to learn rich representations in a wide variety of applications which involve abundant unlabeled information. However, existing GCL approaches largel…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗

2023

Graph of Graphs: A New Knowledge Representation Mechanism for Graph Learning (Student Abstract)

Zhwiei Zhen, Yuzhou Chen, Murat Kantarcioglu, Yulia R. Gel

AAAI 2023technical

Supervised graph classification is one of the most actively developing areas in machine learning (ML), with a broad range of domain applications, from social media to bioinformatics. Given a collection of graphs with categorical labels, the goal is to predict correct classes for unlabelled graphs. H…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Topological Pooling on Graphs

Yuzhou Chen, Yulia R. Gel

AAAI 2023technical

Graph neural networks (GNNs) have demonstrated a significant success in various graph learning tasks, from graph classification to anomaly detection. There recently has emerged a number of approaches adopting a graph pooling operation within GNNs, with a goal to preserve graph attributive and struct…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗

2022

BScNets: Block Simplicial Complex Neural Networks

Yuzhou Chen, Yulia R. Gel, H. Vincent Poor

AAAI 2022technical

Simplicial neural networks (SNNs) have recently emerged as a new direction in graph learning which expands the idea of convolutional architectures from node space to simplicial complexes on graphs. Instead of predominantly assessing pairwise relations among nodes as in the current practice, simplici…

Cited by 42 Source ↗PDF ↗code ↗Scholar ↗

2021

Defending against Backdoors in Federated Learning with Robust Learning Rate

Mustafa Safa Ozdayi, Murat Kantarcioglu, Yulia R. Gel

AAAI 2021technical

Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial attacks due to decentralized and unvetted data. One importa…

Cited by 218 Source ↗PDF ↗code ↗Scholar ↗

2021

Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting

Yuzhou Chen, Ignacio Segovia, Yulia R. Gel

ICML 2021spotlight

There recently has been a surge of interest in developing a new class of deep learning (DL) architectures that integrate an explicit time dimension as a fundamental building block of learning and representation mechanisms. In turn, many recent results show that topological descriptors of the observe…

Cited by 183 Source ↗PDF ↗code ↗Scholar ↗

2020

BitcoinHeist: Topological Data Analysis for Ransomware Prediction on the Bitcoin Blockchain

Cuneyt G. Akcora, Yitao Li, Yulia R. Gel, Murat Kantarcioglu

IJCAI 2020poster

Recent proliferation of cryptocurrencies that allow for pseudo-anonymous transactions has resulted in a spike of various e-crime activities and, particularly, cryptocurrency payments in hacking attacks demanding ransom by encrypting sensitive user data. Currently, most hackers use Bitcoin for paymen…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗