A5085617225- Advanced Graph Neural Networks
- Topological and Geometric Data Analysis
- Neural Networks and Applications
- Complex Network Analysis Techniques
- Bioinformatics and Genomic Networks
- Cell Image Analysis Techniques
- Image Retrieval and Classification Techniques
- Dementia and Cognitive Impairment Research
- Computational Physics and Python Applications
- Semantic Web and Ontologies
- Data Visualization and Analytics
- Privacy-Preserving Technologies in Data
- Natural Language Processing Techniques
- Domain Adaptation and Few-Shot Learning
Sapienza University of Rome
2023
This paper describes the 2nd edition of ICML Topological Deep Learning Challenge that was hosted within 2024 ELLIS Workshop on Geometry-grounded Representation and Generative Modeling (GRaM). The challenge focused problem representing data in different discrete topological domains order to bridge gap between (TDL) other types structured datasets (e.g. point clouds, graphs). Specifically, participants were asked design implement liftings, i.e. mappings structures --like hypergraphs, or...
Latent Graph Inference (LGI) relaxed the reliance of Neural Networks (GNNs) on a given graph topology by dynamically learning it. However, most LGI methods assume to have (noisy, incomplete, improvable, ...) input rewire and can solely learn regular topologies. In wake success Topological Deep Learning (TDL), we study Topology (LTI) for higher-order cell complexes (with sparse not topology) describing multi-way interactions between data points. To this aim, introduce Differentiable Cell...
We introduce topox, a Python software suite that provides reliable and user-friendly building blocks for computing machine learning on topological domains extend graphs: hypergraphs, simplicial, cellular, path combinatorial complexes. topox consists of three packages: toponetx facilitates constructing these domains, including working with nodes, edges higher-order cells; topoembedx methods to embed into vector spaces, akin popular graph-based embedding algorithms such as node2vec; topomodelx...
This work introduces TopoBenchmarkX, a modular open-source library designed to standardize benchmarking and accelerate research in Topological Deep Learning (TDL). TopoBenchmarkX maps the TDL pipeline into sequence of independent components for data loading processing, as well model training, optimization, evaluation. organization provides flexibility modifications facilitates adaptation optimization various pipelines. A key feature is that it allows transformation lifting between...
Graph Neural Networks based on the message-passing (MP) mechanism are a dominant approach for handling graph-structured data. However, they inherently limited to modeling only pairwise interactions, making it difficult explicitly capture complexity of systems with $n$-body relations. To address this, topological deep learning has emerged as promising field studying and higher-order interactions using various domains, such simplicial cellular complexes. While these new domains provide...
Recently emerged Topological Deep Learning (TDL) methods aim to extend current Graph Neural Networks (GNN) by naturally processing higher-order interactions, going beyond the pairwise relations and local neighborhoods defined graph representations. In this paper we propose a novel TDL-based method for compressing signals over graphs, consisting in two main steps: first, disjoint sets of structures are inferred based on original signal --by clustering $N$ datapoints into $K\ll N$ collections;...
Most of the current hypergraph learning methodologies and benchmarking datasets in realm are obtained by lifting procedures from their graph analogs, leading to overshadowing specific characteristics hypergraphs. This paper attempts confront some pending questions that regard: Q1 Can concept homophily play a crucial role Hypergraph Neural Networks (HNNs)? Q2 Is there room for improving HNN architectures carefully addressing higher-order networks? Q3 Do existing provide meaningful benchmark...
The surge in computer network traffic, fueled by emerging applications and technology advancements, is creating a pressing need for efficient techniques to store analyze massive traffic traces. This paper introduces novel approach address this challenge employing Topological Deep Learning (TDL) lossy compression. Unlike Graph Neural Networks (GNNs), which rely on the binary interactions local neighborhoods defined graph representations, TDL methods can naturally accommodate higher-order...
Missing data imputation (MDI) is crucial when dealing with tabular datasets across various domains. Autoencoders can be trained to reconstruct missing values, and graph autoencoders (GAE) additionally consider similar patterns in the dataset imputing new values for a given instance. However, previously proposed GAEs suffer from scalability issues, requiring user define similarity metric among build connectivity beforehand. In this paper, we leverage recent progress latent propose novel EdGe...
This paper presents the computational challenge on topological deep learning that was hosted within ICML 2023 Workshop Topology and Geometry in Machine Learning. The competition asked participants to provide open-source implementations of neural networks from literature by contributing python packages TopoNetX (data processing) TopoModelX (deep learning). attracted twenty-eight qualifying submissions its two-month duration. describes design summarizes main findings.