Compositional Concept Generalization with Variational Quantum Circuits
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909782050340864 |
|---|---|
| author | Hawashin, Hala Abbaszadeh, Mina Joseph, Nicholas Pearson, Beth Lewis, Martha sadrzadeh, Mehrnoosh |
| author_facet | Hawashin, Hala Abbaszadeh, Mina Joseph, Nicholas Pearson, Beth Lewis, Martha sadrzadeh, Mehrnoosh |
| contents | Compositional generalization is a key facet of human cognition, but lacking in current AI tools such as vision-language models. Previous work examined whether a compositional tensor-based sentence semantics can overcome the challenge, but led to negative results. We conjecture that the increased training efficiency of quantum models will improve performance in these tasks. We interpret the representations of compositional tensor-based models in Hilbert spaces and train Variational Quantum Circuits to learn these representations on an image captioning task requiring compositional generalization. We used two image encoding techniques: a multi-hot encoding (MHE) on binary image vectors and an angle/amplitude encoding on image vectors taken from the vision-language model CLIP. We achieve good proof-of-concept results using noisy MHE encodings. Performance on CLIP image vectors was more mixed, but still outperformed classical compositional models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_09541 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Compositional Concept Generalization with Variational Quantum Circuits Hawashin, Hala Abbaszadeh, Mina Joseph, Nicholas Pearson, Beth Lewis, Martha sadrzadeh, Mehrnoosh Artificial Intelligence Compositional generalization is a key facet of human cognition, but lacking in current AI tools such as vision-language models. Previous work examined whether a compositional tensor-based sentence semantics can overcome the challenge, but led to negative results. We conjecture that the increased training efficiency of quantum models will improve performance in these tasks. We interpret the representations of compositional tensor-based models in Hilbert spaces and train Variational Quantum Circuits to learn these representations on an image captioning task requiring compositional generalization. We used two image encoding techniques: a multi-hot encoding (MHE) on binary image vectors and an angle/amplitude encoding on image vectors taken from the vision-language model CLIP. We achieve good proof-of-concept results using noisy MHE encodings. Performance on CLIP image vectors was more mixed, but still outperformed classical compositional models. |
| title | Compositional Concept Generalization with Variational Quantum Circuits |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2509.09541 |