Tobias Fuchs, Nadja Klein
We lifted 4 functions out of this paper's own repositories and ran 0 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 |
|---|---|---|
| mathefuchs/vi-pll | canonical | 0 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| flatten_if_image | Not yet run | mathefuchs/vi-pll/partial_label_learning/data.py code served (permissive licence) · get_code("d3e66da794d5b4ec") |
| get_model_arch | Not yet run | mathefuchs/vi-pll/models/model_util.py code served (permissive licence) · get_code("a120b4d24742c976") |
| main | Not yet run | mathefuchs/vi-pll/vi_results.py code served (permissive licence) · get_code("005695f982f5e386") |
| random_class_imbalance | Not yet run | mathefuchs/vi-pll/partial_label_learning/data.py code served (permissive licence) · get_code("0e119ef9e1886b05") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Real-world data is frequently noisy and ambiguous. In crowdsourcing, for example, human annotators may assign conflicting class labels to the same instances. Partial-label learning (PLL) addresses this challenge by training classifiers when each instance is associated with a set of candidate labels, only one of which is correct. While early PLL methods approximate the true label posterior, they are often computationally intensive. Recent deep learning approaches improve scalability but rely on surrogate losses and heuristic label refinement. We introduce a novel probabilistic framework that directly approximates the posterior distribution over true labels using amortized variational inference. Our method employs neural networks to predict variational parameters from input data, enabling efficient inference. This approach combines the expressiveness of deep learning with the rigor of probabilistic modeling, while remaining architecture-agnostic. Theoretical analysis and extensive experiments on synthetic and real-world datasets demonstrate that our method achieves state-of-the-art performance in both accuracy and efficiency.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2510.21300")
get_code_for_paper("2510.21300")
have("2510.21300")
Connect an agent — have() is free.