Chao Chen, Pengxiang Wu, Songzhu Zheng, Mayank Goswami, Yikai Zhang
We lifted 1 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 |
|---|---|---|
| pxiangwu/PLC | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| lrt_correction | Ran | pxiangwu/PLC/utils.py pointer only (licence: NONE) · get_code("0601f87d551dbdd2") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing approaches to handling noisy labels fall into two categories: they either assume an ideal feature-independent noise, or remain heuristic without theoretical guarantees. In this paper, we propose to target a new family of featuredependent label noise, which is much more general than commonly used i.i.d. label noise and encompasses a broad spectrum of noise patterns. Focusing on this general noise family, we propose a progressive label correction algorithm that iteratively corrects labels and refines the model. We provide theoretical guarantees showing that for a wide variety of (unknown) noise patterns, a classifier trained with this strategy converges to be consistent with the Bayes classifier. In experiments, our method outperforms SOTA baselines and is robust to various noise types and levels.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2103.07756")
get_code_for_paper("2103.07756")
have("2103.07756")
Connect an agent — have() is free.