We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| asparius/unsee | canonical | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| byol_fn | Ran | asparius/unsee/sentence_transformers/losses/BYOLoss.py code served (permissive licence) · get_code("7765bc8a5595b134") |
| off_diagonal | Ran | asparius/unsee/sentence_transformers/losses/BYOLoss.py code served (permissive licence) · get_code("3e30d88eaef01190") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation collapse, a phenomenon observed when contrastive objectives in SimCSE are replaced with non-contrastive objectives. To counter this issue, we propose a straightforward solution known as the target network, effectively mitigating representation collapse. The introduction of the target network allows us to leverage non-contrastive objectives, maintaining training stability while achieving performance improvements comparable to contrastive objectives. Our method has achieved peak performance in non-contrastive sentence embeddings through meticulous fine-tuning and optimization. This comprehensive effort has yielded superior sentence representation models, showcasing the effectiveness of our approach.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2401.15316")
get_code_for_paper("2401.15316")
have("2401.15316")
Connect an agent — have() is free.