Gated Graph Sequence Neural Networks
Authors: Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel, CIFAR
ICLR 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the capabilities on some simple AI (b Ab I) and graph algorithm learning tasks. We then show it achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be described as abstract data structures. |
| Researcher Affiliation | Collaboration | Yujia Li & Richard Zemel Department of Computer Science, University of Toronto Toronto, Canada {yujiali,zemel}@cs.toronto.edu Marc Brockschmidt & Daniel Tarlow Microsoft Research Cambridge, UK {mabrocks,dtarlow}@microsoft.com Work done primarily while author was an intern at Microsoft Research. |
| Pseudocode | Yes | Algorithm 1 Separation logic formula prediction procedure Input: Heap graph G with named program variables. Algorithm 2 Nested separation logic formula prediction procedure. |
| Open Source Code | No | The paper mentions using "the --symbolic option from the released b Ab I code" but does not state that the authors are releasing their own code for the GGS-NN methodology or providing a link to it. |
| Open Datasets | Yes | In this section we present example applications that concretely illustrate the use of GGS-NNs. We focus on a selection of b Ab I artificial intelligence (AI) tasks (Weston et al., 2015) and two graph algorithm learning tasks. |
| Dataset Splits | Yes | For all tasks in this section, we generate 1000 training examples and 1000 test examples, 50 of the training examples are used for validation. |
| Hardware Specification | No | The paper does not explicitly describe the hardware used for running its experiments, such as specific GPU or CPU models. |
| Software Dependencies | No | The paper mentions "Adam (Kingma & Ba, 2014)" as an optimizer but does not provide specific version numbers for any software dependencies or libraries used for implementation (e.g., PyTorch, TensorFlow, scikit-learn versions). |
| Experiment Setup | Yes | For all explanatory tasks, we start by training different models on only 50 training examples, and gradually increase the number of training examples to 100, 250, 500, and 950 (50 of the training examples are reserved for validation) until the model s test accuracy reaches 95% or above, a success by b Ab I standard Weston et al. (2015). For each method, we report the minimum number of training examples it needs to reach 95% accuracy along with the accuracy it reaches with that amount of training examples. In all these cases, we unrolled the propagation process for 5 steps. For b Ab I task 4, 15, 16, 18, 19, we used GG-NN with the size of node vectors h(t) v set to D = 4, D = 5, D = 6, D = 3 and D = 6 respectively. For all the GGS-NNs in this section we used the simpler variant in which F(k) o and F(k) X share a single propagation model. For shortest path and Eulerian circuit tasks, we used D = 20. All models are trained long enough with Adam (Kingma & Ba, 2014), and the validation set is used to choose the best model to evaluate and avoid models that are overfitting. |