From 20f5c094563d62a99dc0d51e6d171a140ff23441 Mon Sep 17 00:00:00 2001 From: Gao Enhao Date: Mon, 8 Jan 2024 12:32:08 +0800 Subject: [PATCH] [ENH] add mnist performance to docs --- docs/Examples/MNISTAdd.rst | 6 ++++++ examples/mnist_add/README.md | 16 ++++++++++++++++ examples/mnist_add/mnist_add.ipynb | 10 ++++++++++ 3 files changed, 32 insertions(+) diff --git a/docs/Examples/MNISTAdd.rst b/docs/Examples/MNISTAdd.rst index dbf438e..a5a2543 100644 --- a/docs/Examples/MNISTAdd.rst +++ b/docs/Examples/MNISTAdd.rst @@ -392,6 +392,12 @@ Log: Performance ----------- +We present the results of ABL as follows, which include the reasoning accuracy (the proportion of equations that are correctly summed), and the training time used to achieve this accuracy. These results are compared with the following methods: + +- `NeurASP `_: An extension of answer set programs by treating the neural network output as the probability distribution over atomic facts; +- `DeepProbLog `_: An extension of ProbLog by introducing neural predicates in Probabilistic Logic Programming; +- `DeepStochLog `_: A neural-symbolic framework based on stochastic logic program. + .. table:: :class: centered diff --git a/examples/mnist_add/README.md b/examples/mnist_add/README.md index 98254ab..c9f24c6 100644 --- a/examples/mnist_add/README.md +++ b/examples/mnist_add/README.md @@ -43,3 +43,19 @@ optional arguments: --ground use GroundKB (default: False) ``` + + +## Performance + +We present the results of ABL as follows, which include the reasoning accuracy (the proportion of equations that are correctly summed), and the training time used to achieve this accuracy. These results are compared with the following methods: + +- [**NeurASP**](https://github.com/azreasoners/NeurASP): An extension of answer set programs by treating the neural network output as the probability distribution over atomic facts; +- [**DeepProbLog**](https://github.com/ML-KULeuven/deepproblog): An extension of ProbLog by introducing neural predicates in Probabilistic Logic Programming; +- [**DeepStochLog**](https://github.com/ML-KULeuven/deepstochlog): A neural-symbolic framework based on stochastic logic program. + +| Method | Accuracy | Time to achieve the Acc. (s) | +| :----------: | :------: | :--------------------------: | +| NeurASP | 0.964 | 354 | +| DeepProbLog | 0.965 | 1965 | +| DeepStochLog | 0.975 | 727 | +| ABL | 0.980 | 42 | \ No newline at end of file diff --git a/examples/mnist_add/mnist_add.ipynb b/examples/mnist_add/mnist_add.ipynb index 0c947b3..0cda102 100644 --- a/examples/mnist_add/mnist_add.ipynb +++ b/examples/mnist_add/mnist_add.ipynb @@ -465,6 +465,16 @@ "## Performance" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We present the results of ABL as follows, which include the reasoning accuracy (the proportion of equations that are correctly summed), and the training time used to achieve this accuracy. These results are compared with the following methods:\n", + "- [**NeurASP**](https://github.com/azreasoners/NeurASP): An extension of answer set programs by treating the neural network output as the probability distribution over atomic facts;\n", + "- [**DeepProbLog**](https://github.com/ML-KULeuven/deepproblog): An extension of ProbLog by introducing neural predicates in Probabilistic Logic Programming;\n", + "- [**DeepStochLog**](https://github.com/ML-KULeuven/deepstochlog): A neural-symbolic framework based on stochastic logic program." + ] + }, { "cell_type": "markdown", "metadata": {},