The Role of Representation Learning in Advancing Deep Learning: Efficiency, Scalability, and Reasoning


Loading...

Date

2025

Publication Type

Doctoral Thesis

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

This thesis explores the multifaceted role of representation learning in improving the performance of deep neural networks in various applications. We delve into the paradigm of active learning, investigating its application in iterative combinatorial auctions and the integration of diversity and uncertainty-based sampling strategies in the context of self-supervised, pre-trained models. Our exploration extends to disentangled representation learning, where we introduce a novel training procedure for variational autoencoders that overcomes the challenge of hyperparameter selection and enables consistent learning of disentangled representations. We also leverage implicit neural representations for domain-agnostic super-resolution, demonstrating the ability to upscale any arbitrary data type. In addition, we address the challenge of scaling transformers to large inputs by proposing a hierarchical tree-based architecture. Finally, we investigate the reasoning capabilities of large language models. We demonstrate the feasibility of using language for reasoning in abstract visual tasks. We then introduce a benchmark for evaluating algorithmic reasoning and analyze the scaling behavior of reasoning language models on complex logic puzzles. Through these diverse investigations, this thesis contributes to a deeper understanding of representation learning and its potential to advance the development of more robust, efficient, and intelligent AI systems.

Publication status

published

Editor

Contributors

Examiner : Wattenhofer, Roger
Examiner : Martius, Georg

Book title

Journal / series

Volume

Pages / Article No.

Publisher

ETH Zurich

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Representation learning; Reasoning; Active learning

Organisational unit

03604 - Wattenhofer, Roger / Wattenhofer, Roger

Notes

Funding

Related publications and datasets