We lifted 3 functions out of this paper's own repositories and ran 1 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 |
|---|---|---|
| jdcomsearch/poeem | canonical | 1 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| compute_distortion | Ran | jdcomsearch/poeem/src/python/embedding.py code served (permissive licence) · get_code("06339b9bd192f3e1") |
| compute_rotation | Not yet run | jdcomsearch/poeem/src/python/embedding.py code served (permissive licence) · get_code("6d8bad237377c500") |
| encode | Not yet run | jdcomsearch/poeem/src/ops/python/encode.py code served (permissive licence) · get_code("d3edc68ba2422435") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Embedding index that enables fast approximate nearest neighbor(ANN) search, serves as an indispensable component for state-of-the-art deep retrieval systems. Traditional approaches, often separating the two steps of embedding learning and index building, incur additional indexing time and decayed retrieval accuracy. In this paper, we propose a novel method called Poeem, which stands for product quantization based embedding index jointly trained with deep retrieval model, to unify the two separate steps within an end-to-end training, by utilizing a few techniques including the gradient straight-through estimator, warm start strategy, optimal space decomposition and Givens rotation. Extensive experimental results show that the proposed method not only improves retrieval accuracy significantly but also reduces the indexing time to almost none. We have open sourced our approach for the sake of comparison and reproducibility.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2105.03933")
get_code_for_paper("2105.03933")
have("2105.03933")
Connect an agent — have() is free.