Notice: 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. Full accuracy metrics and methodology are described in [1].
Meta-Learning with Fewer Tasks through Task Interpolation
Authors: Huaxiu Yao, Linjun Zhang, Chelsea Finn
ICLR 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirically, in our experiments on eight datasets from diverse domains including image recognition, pose prediction, molecule property prediction, and medical image classification, we find that the proposed general MLTI framework is compatible with representative meta-learning algorithms and consistently outperforms other state-of-the-art strategies. |
| Researcher Affiliation | Academia | Huaxiu Yao1, Linjun Zhang2, Chelsea Finn1 1Stanford University, 2Rutgers University 1EMAIL, EMAIL |
| Pseudocode | Yes | A PSEUDOCODES In this section, we show the pseudocodes for MLTI with MAML (meta-training process: Alg. 1, meta-testing process: Alg. 2) and Proto Net (meta-training process: Alg. 3, meta-testing process: Alg. 4). |
| Open Source Code | Yes | REPRODUCIBILITY STATEMENT... Code: https://github.com/huaxiuyao/MLTI. |
| Open Datasets | Yes | We perform experiments on four datasets to evaluate the performance of MLTI: (1) PASCAL3D Pose regression (Pose) (Yin et al., 2020)... (2) Rainbow MNIST (RMNIST) (Finn et al., 2019)... (3)&(4) NCI (NCI, 2018) and TDC Metabolism (Metabolism) (Huang et al., 2021)... (1) general image classification on mini Imagenet (Vinyals et al., 2016); (2)&(3) medical image classification on ISIC (Milton, 2019) and Derm Net (Der, 2016); and (4) cell type classification across organs on Tabular Murris (Cao et al., 2021). |
| Dataset Splits | Yes | Rainbow MNIST (RMNIST)...We use 16/6/10 subdatasets for meta-training/validation/testing and list their corresponding combinations of image transformations as follows... In Tabular Murris, the base model contains two fully connected blocks and a linear regressor, where each fully connected block contains a linear layer, a batch normalization layer, a Re LU activation layer, and a dropout layer. Follow Cao et al. (2021), the default dropout ratio and the output channels of the linear layer are set as 0.2, 64, respectively. We apply Mainfold Mixup (Verma et al., 2019) as the interpolation strategy. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used to run its experiments. |
| Software Dependencies | No | The paper mentions specific tools like "RDKit (Landrum, 2016)" and "ALBERT (Lan et al., 2019)", but it does not specify version numbers for general software dependencies like Python, PyTorch, TensorFlow, or other common libraries used in the experimental setup. |
| Experiment Setup | Yes | All hyperparameters are listed in Table 5, which are selected by the cross-validation. Notice that all baselines use the same base models and interpolation-based methods (i.e., Meta Mix, Meta-Maxup, MLTI) use the same interpolation strategies. Table 7: Hyperparameters under the non-label-sharing scenario. |