Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks
Authors: Yijun Tian, Chuxu Zhang, Zhichun Guo, Yihong Ma, Ronald Metoyer, Nitesh V. Chawla
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate that Recipe2Vec outperforms state-of-the-art baselines on two classic food study tasks, i.e., cuisine category classification and region prediction. |
| Researcher Affiliation | Academia | 1Department of Computer Science, University of Notre Dame, USA 2Department of Computer Science, Brandeis University, USA |
| Pseudocode | No | The paper describes its model and algorithms using prose and mathematical equations but does not include explicit pseudocode blocks or algorithms labeled as such. |
| Open Source Code | Yes | Dataset and codes are available at https://github.com/meettyj/Recipe2Vec. |
| Open Datasets | Yes | Specifically, we first collect recipes from Recipe1M [Marin et al., 2019] and crawl the user ratings for each recipe from food.com. We then match each ingredient to the USDA nutritional database [USDA, 2019] to determine its nutritional value. |
| Dataset Splits | Yes | We split the data into train/validation/test set by 70/15/15. |
| Hardware Specification | No | The paper does not specify the hardware (e.g., GPU model, CPU type) used for running the experiments. It only describes the experimental setup in terms of hyperparameters and dataset splits. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies or libraries used for implementation (e.g., Python, PyTorch, TensorFlow versions). It mentions tools like LSTM and ResNet as components but not their software versions. |
| Experiment Setup | Yes | For the proposed Recipe2Vec, we set the learning rate to 0.005, the hidden size to 128, the input dimension of instruction and image embeddings to 512, the input dimension of ingredient embeddings to 46, batch size to 4096, meta-path P to recipe-user-recipe, the number of meta-path neighbors p to 10, training epochs to 100, the trade-off factor λ to 0.1, the perturbation range S to 0.02, number of iterations for attack to 5, and the attack step size to 0.005. |