1165 København K
Tlf: 21 17 95 65 (man-fre kl. 9-15)
Ph.d.-forsvar — On 16 August Casper Hansen will defend his PhD thesis titled "Representation Learning for Efficient and Effective Similarity Search and Recommendation".
Date & Time:
Department of Computer Science
Representation Learning for Efficient and Effective Similarity Search and Recommendation
How data is represented and operationalized is critical for building computational solutions that are both effective and efficient. A common approach is to represent data objects as binary vectors, denoted hash codes, which require little storage and enable efficient similarity search through direct indexing into a hash table or through similarity computations in an appropriate space. Due to the limited expressibility of hash codes, compared to real-valued representations, a core open challenge is how to generate hash codes that well capture semantic content or latent properties using a small number of bits, while ensuring that the hash codes are distributed in a way that does not reduce their search efficiency. State of the art methods use representation learning for generating such hash codes, focusing on neural autoencoder architectures where semantics are encoded into the hash codes by learning to reconstruct the original inputs of the hash codes. This thesis addresses the above challenge and makes a number of contributions to representation learning that (i) improve effectiveness of hash codes through more expressive representations and a more effective similarity measure than the current state of the art, namely the Hamming distance, and (ii) improve efficiency of hash codes by learning representations that are especially suited to the choice of search method. The contributions are empirically validated on several tasks related to similarity search and recommendation.
Associate Professor Daniel Spikol, Machine Learning Section at Department of Computer Science, UCPH.
For a digital version of the thesis, please visit: https://di.ku.dk/english/research/phd/.