Related papers: Masked BRep Autoencoder via Hierarchical Graph Tra…
Graphs are ubiquitous in real-world scenarios and encompass a diverse range of tasks, from node-, edge-, and graph-level tasks to transfer learning. However, designing specific tasks for each type of graph data is often costly and lacks…
Graph autoencoders (GAEs) are powerful tools in representation learning for graph embedding. However, the performance of GAEs is very dependent on the quality of the graph structure, i.e., of the adjacency matrix. In other words, GAEs would…
Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of the input data need to be captured by the codes. Kernel…
Graph representation learning is a fast-growing field where one of the main objectives is to generate meaningful representations of graphs in lower-dimensional spaces. The learned embeddings have been successfully applied to perform various…
Machine learning is typically framed from a perspective of i.i.d., and more importantly, isolated data. In parts, federated learning lifts this assumption, as it sets out to solve the real-world challenge of collaboratively learning a…
In this work, we introduce Mask-JEPA, a self-supervised learning framework tailored for mask classification architectures (MCA), to overcome the traditional constraints associated with training segmentation models. Mask-JEPA combines a…
Building scalable models to learn from diverse, multimodal data remains an open challenge. For vision-language data, the dominant approaches are based on contrastive learning objectives that train a separate encoder for each modality. While…
Geometric trees are characterized by their tree-structured layout and spatially constrained nodes and edges, which significantly impacts their topological attributes. This inherent hierarchical structure plays a crucial role in domains such…
Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the…
Although substantial efforts have been made using graph neural networks (GNNs) for AI-driven drug discovery (AIDD), effective molecular representation learning remains an open challenge, especially in the case of insufficient labeled…
We propose a novel machine learning strategy for studying neuroanatomical shape variation. Our model works with volumetric binary segmentation images, and requires no pre-processing such as the extraction of surface points or a mesh. The…
Streets networks provide an invaluable source of information about the different temporal and spatial patterns emerging in our cities. These streets are often represented as graphs where intersections are modelled as nodes and streets as…
Using a convGRU-based autoencoder, this thesis proposes a framework to learn spatial-temporal aspects of raw network traffic in an unsupervised and protocol-agnostic manner. The learned representations are used to measure the effect on the…
Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on the use of graphs to represent chemical molecules, we explore the task of learning to generate graphs that conform to a distribution…
With the growing interest in foundation models for brain signals, graph-based pretraining has emerged as a promising paradigm for learning transferable representations from connectome data. However, existing contrastive and masked…
Causal structure learning has been a challenging task in the past decades and several mainstream approaches such as constraint- and score-based methods have been studied with theoretical guarantees. Recently, a new approach has transformed…
Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-based pretraining task. However, their performance is often…
Despite decades of research, understanding human manipulation activities is, and has always been, one of the most attractive and challenging research topics in computer vision and robotics. Recognition and prediction of observed human…
With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features…
Autoencoders have achieved great success in various computer vision applications. The autoencoder learns appropriate low dimensional image representations through the self-supervised paradigm, i.e., reconstruction. Existing studies mainly…