Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
A Nested Bi-level Optimization Framework for Robust Few Shot Learning
Authors: Krishnateja Killamsetty, Changbin Li, Chen Zhao, Feng Chen, Rishabh Iyer7176-7184
AAAI 2022 | Venue PDF | LLM Run Details | Input Tokens: 18,462 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,496 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on synthetic and real-world datasets demonstrate that NESTEDMAML efficiently mitigates the effects of unwanted tasks or instances, leading to significant improvement over the state-of-the-art robust meta-learning methods. |
| Researcher Affiliation | Academia | The University of Texas at Dallas, Richardson, Texas, USA EMAIL |
| Pseudocode | Yes | Algorithm 1: NESTEDMAML |
| Open Source Code | Yes | We performed all the experiments using Py Torch, and the code is available at https://github.com/Hugo101/NestedMAML. |
| Open Datasets | Yes | We use mini-Image Net (Ravi and Larochelle 2016), SVHN (Netzer et al. 2011), Fashion MNIST (Xiao, Rasul, and Vollgraf 2017) datasets in our experiments. |
| Dataset Splits | Yes | We sample the ID tasks (meta-training, metavalidation, and meta-test) from the mini-Image Net dataset and sample OOD tasks from the SVHN or the Fashion MNIST dataset. |
| Hardware Specification | No | The paper does not specify the hardware (e.g., GPU/CPU models, memory) used for experiments. |
| Software Dependencies | No | The paper mentions 'Py Torch' but does not provide a specific version number for it or any other software dependencies. |
| Experiment Setup | Yes | Settings. We implement image classification experiments in 5-way, 3-shot (5-shot) settings. And we use a model with similar backbone architecture given in (Vinyals et al. 2016; Finn, Abbeel, and Levine 2017) for all baselines. We consider a total of 20,000 training tasks containing both ID and OOD tasks where the split of ID and OOD tasks is determined by OOD ratio(0.3, 0.6, and 0.9 in this setting). At each iteration, ID tasks and OOD tasks will be sampled according to the OOD ratio. |