diff --git a/.github/citation/citation.json b/.github/citation/citation.json index 86c161c..65b04aa 100644 --- a/.github/citation/citation.json +++ b/.github/citation/citation.json @@ -1 +1 @@ -{"Neurologic decoding:(un) supervised neural text generation with predicate logic constraints": {"citation": 125, "last update": "2024-09-19"}, "A review of some techniques for inclusion of domain-knowledge into deep neural networks": {"citation": 147, "last update": "2024-09-19"}, "Informed machine learning-a taxonomy and survey of integrating prior knowledge into learning systems": {"citation": 749, "last update": "2024-09-19"}, "The Connectionist Inductive Learning and Logic Programming System": {"citation": 252, "last update": "2024-09-21"}, "Harnessing Deep Neural Networks with Logic Rules": {"citation": 771, "last update": "2024-09-21"}, "Deep Learning with Logical Constraints": {"citation": 63, "last update": "2024-09-21"}, "A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints": {"citation": 5, "last update": "2024-09-21"}, "Hyper-class Augmented and Regularized Deep Learning for Fine-grained Image Classification": {"citation": 236, "last update": "2024-09-21"}, "Injecting Logical Constraints into Neural Networks via Straight-Through Estimators": {"citation": 22, "last update": "2024-09-21"}, "Rewriting a Deep Generative Model": {"citation": 125, "last update": "2024-09-21"}, "DeepProbLog: Neural Probabilistic Logic Programming": {"citation": 612, "last update": "2024-09-21"}, "Guided Open Vocabulary Image Captioning with Constrained Beam Search": {"citation": 255, "last update": "2024-09-21"}, "DeepEdit: Knowledge Editing as Decoding with Constraints": {"citation": 11, "last update": "2024-09-21"}, "Don't Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation": {"citation": 25, "last update": "2024-09-21"}, "VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images": {"citation": 233, "last update": "2024-09-21"}, "MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks": {"citation": 54, "last update": "2024-09-21"}, "Interpretability Beyond Feature Attribution:Quantitative Testing with Concept Activation Vectors (TCAV)": {"citation": 1993, "last update": "2024-09-21"}, "Label-free Concept Bottleneck Models": {"citation": 105, "last update": "2024-09-21"}, "Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification": {"citation": 143, "last update": "2024-09-21"}, "Editing a classifier by rewriting its prediction rules": {"citation": 73, "last update": "2024-09-21"}, "Concept Bottleneck Models": {"citation": 732, "last update": "2024-09-21"}, "Interactive Concept Bottleneck Models": {"citation": 41, "last update": "2024-09-21"}, "Promises and Pitfalls of Black-Box Concept Learning Models": {"citation": 80, "last update": "2024-09-21"}, "Addressing Leakage in Concept Bottleneck Models": {"citation": 50, "last update": "2024-09-21"}, "CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning": {"citation": 343, "last update": "2024-09-21"}, "POST-HOC CONCEPT BOTTLENECK MODELS": {"citation": 159, "last update": "2024-09-21"}, "Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat": {"citation": 7, "last update": "2024-09-21"}, "A Semantic Loss Function for Deep Learning with Symbolic Knowledge": {"citation": 530, "last update": "2024-09-21"}} \ No newline at end of file +{"Neurologic decoding:(un) supervised neural text generation with predicate logic constraints": {"citation": 125, "last update": "2024-09-24"}, "A review of some techniques for inclusion of domain-knowledge into deep neural networks": {"citation": 147, "last update": "2024-09-24"}, "Informed machine learning-a taxonomy and survey of integrating prior knowledge into learning systems": {"citation": 757, "last update": "2024-09-24"}, "The Connectionist Inductive Learning and Logic Programming System": {"citation": 252, "last update": "2024-09-24"}, "Harnessing Deep Neural Networks with Logic Rules": {"citation": 772, "last update": "2024-09-24"}, "Deep Learning with Logical Constraints": {"citation": 63, "last update": "2024-09-24"}, "A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints": {"citation": 5, "last update": "2024-09-24"}, "Hyper-class Augmented and Regularized Deep Learning for Fine-grained Image Classification": {"citation": 236, "last update": "2024-09-24"}, "Injecting Logical Constraints into Neural Networks via Straight-Through Estimators": {"citation": 22, "last update": "2024-09-24"}, "Rewriting a Deep Generative Model": {"citation": 125, "last update": "2024-09-24"}, "DeepProbLog: Neural Probabilistic Logic Programming": {"citation": 613, "last update": "2024-09-24"}, "Guided Open Vocabulary Image Captioning with Constrained Beam Search": {"citation": 255, "last update": "2024-09-24"}, "DeepEdit: Knowledge Editing as Decoding with Constraints": {"citation": 11, "last update": "2024-09-24"}, "Don't Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation": {"citation": 25, "last update": "2024-09-24"}, "VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images": {"citation": 235, "last update": "2024-09-24"}, "MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks": {"citation": 54, "last update": "2024-09-24"}, "Interpretability Beyond Feature Attribution:Quantitative Testing with Concept Activation Vectors (TCAV)": {"citation": 1996, "last update": "2024-09-24"}, "Label-free Concept Bottleneck Models": {"citation": 105, "last update": "2024-09-24"}, "Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification": {"citation": 143, "last update": "2024-09-24"}, "Editing a classifier by rewriting its prediction rules": {"citation": 73, "last update": "2024-09-24"}, "Concept Bottleneck Models": {"citation": 736, "last update": "2024-09-24"}, "Interactive Concept Bottleneck Models": {"citation": 41, "last update": "2024-09-24"}, "Promises and Pitfalls of Black-Box Concept Learning Models": {"citation": 81, "last update": "2024-09-24"}, "Addressing Leakage in Concept Bottleneck Models": {"citation": 50, "last update": "2024-09-24"}, "CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning": {"citation": 343, "last update": "2024-09-24"}, "POST-HOC CONCEPT BOTTLENECK MODELS": {"citation": 160, "last update": "2024-09-24"}, "Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat": {"citation": 7, "last update": "2024-09-24"}, "A Semantic Loss Function for Deep Learning with Symbolic Knowledge": {"citation": 530, "last update": "2024-09-24"}} \ No newline at end of file diff --git a/README.md b/README.md index 7a0c79c..ee2ef1c 100644 --- a/README.md +++ b/README.md @@ -14,13 +14,13 @@ A list of awesome resources related to constraint learning | Venue | Title | Affiliation |       Link       |   Source   | | :---: | :---: | :---------: | :---: | :----: | |IJCAI 2022|Deep Learning with Logical Constraints|University of Oxford| [[paper]](https://arxiv.org/pdf/2205.00523.pdf)![Scholar citations](https://img.shields.io/badge/Citations-63-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)|| -|TKDE 2019|Informed machine learning-a taxonomy and survey of integrating prior knowledge into learning systems|Fraunhofer IAIS| [[paper]](https://arxiv.org/pdf/1903.12394.pdf)![Scholar citations](https://img.shields.io/badge/Citations-749-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)|| +|TKDE 2019|Informed machine learning-a taxonomy and survey of integrating prior knowledge into learning systems|Fraunhofer IAIS| [[paper]](https://arxiv.org/pdf/1903.12394.pdf)![Scholar citations](https://img.shields.io/badge/Citations-757-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)|| |Scientific Reports 2022|A review of some techniques for inclusion of domain-knowledge into deep neural networks|| [[paper]](https://www.nature.com/articles/s41598-021-04590-0)![Scholar citations](https://img.shields.io/badge/Citations-147-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)|| ### Benchmark | Venue | Title | Affiliation |       Link       |   Source   | | :---: | :---: | :---------: | :---: | :----: | |EMNLP 2020|CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning|USC| [[paper]](https://arxiv.org/pdf/1911.03705.pdf)![Scholar citations](https://img.shields.io/badge/Citations-343-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/INK-USC/CommonGen)![GitHub stars](https://img.shields.io/github/stars/INK-USC/CommonGen.svg?logo=github&label=Stars)| -|Medical image analysis 2021|VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images|Technical University of Munich| [[paper]](https://arxiv.org/abs/2001.09193)![Scholar citations](https://img.shields.io/badge/Citations-233-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/anjany/verse)![GitHub stars](https://img.shields.io/github/stars/anjany/verse.svg?logo=github&label=Stars)| +|Medical image analysis 2021|VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images|Technical University of Munich| [[paper]](https://arxiv.org/abs/2001.09193)![Scholar citations](https://img.shields.io/badge/Citations-235-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/anjany/verse)![GitHub stars](https://img.shields.io/github/stars/anjany/verse.svg?logo=github&label=Stars)| ### Data Augmentation | Venue | Title | Affiliation |       Link       |   Source   | | :---: | :---: | :---------: | :---: | :----: | @@ -29,26 +29,26 @@ A list of awesome resources related to constraint learning | Venue | Title | Affiliation |       Link       |   Source   | | :---: | :---: | :---------: | :---: | :----: | |NIPS 2023|A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints|UCLA| [[paper]](https://arxiv.org/pdf/2312.03905.pdf)![Scholar citations](https://img.shields.io/badge/Citations-5-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/UCLA-StarAI/PseudoSL)![GitHub stars](https://img.shields.io/github/stars/UCLA-StarAI/PseudoSL.svg?logo=github&label=Stars)| -|ACL 2016|Harnessing Deep Neural Networks with Logic Rules|CMU| [[paper]](https://arxiv.org/pdf/1603.06318.pdf)![Scholar citations](https://img.shields.io/badge/Citations-771-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/ZhitingHu/logicnn)![GitHub stars](https://img.shields.io/github/stars/ZhitingHu/logicnn.svg?logo=github&label=Stars)| +|ACL 2016|Harnessing Deep Neural Networks with Logic Rules|CMU| [[paper]](https://arxiv.org/pdf/1603.06318.pdf)![Scholar citations](https://img.shields.io/badge/Citations-772-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/ZhitingHu/logicnn)![GitHub stars](https://img.shields.io/github/stars/ZhitingHu/logicnn.svg?logo=github&label=Stars)| |Applied Intelligence 1999|The Connectionist Inductive Learning and Logic Programming System|IC| [[paper]](https://link.springer.com/article/10.1023/A:1008328630915)![Scholar citations](https://img.shields.io/badge/Citations-252-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)|| |ICML 2018|A Semantic Loss Function for Deep Learning with Symbolic Knowledge|UCLA| [[paper]](https://proceedings.mlr.press/v80/xu18h/xu18h.pdf)![Scholar citations](https://img.shields.io/badge/Citations-530-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/UCLA-StarAI/Semantic-Loss)![GitHub stars](https://img.shields.io/github/stars/UCLA-StarAI/Semantic-Loss.svg?logo=github&label=Stars)| |NAACL 2021|Neurologic decoding:(un) supervised neural text generation with predicate logic constraints|UW| [[paper]](https://arxiv.org/pdf/2010.12884.pdf)![Scholar citations](https://img.shields.io/badge/Citations-125-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/GXimingLu/neurologic_decoding)![GitHub stars](https://img.shields.io/github/stars/GXimingLu/neurologic_decoding.svg?logo=github&label=Stars)| |EMNLP 2017|Guided Open Vocabulary Image Captioning with Constrained Beam Search|The Australian National University| [[paper]](https://aclanthology.org/D17-1098.pdf)![Scholar citations](https://img.shields.io/badge/Citations-255-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/nocaps-org/updown-baseline)![GitHub stars](https://img.shields.io/github/stars/nocaps-org/updown-baseline.svg?logo=github&label=Stars)| |NIPS 2022|Don't Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation|NUS| [[paper]](https://diff-tl.github.io/assets/docs/dtl_neurips2022.pdf)![Scholar citations](https://img.shields.io/badge/Citations-25-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/ZiweiXU/DTL-action-segmentation)![GitHub stars](https://img.shields.io/github/stars/ZiweiXU/DTL-action-segmentation.svg?logo=github&label=Stars)| |AAAI 2021|MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks|University of Edinburgh| [[paper]](https://arxiv.org/pdf/2111.01564.pdf)![Scholar citations](https://img.shields.io/badge/Citations-54-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/NickHoernle/semantic_loss)![GitHub stars](https://img.shields.io/github/stars/NickHoernle/semantic_loss.svg?logo=github&label=Stars)| -|NIPS 2018|DeepProbLog: Neural Probabilistic Logic Programming|KU Leuven| [[paper]](https://arxiv.org/pdf/1805.10872.pdf)![Scholar citations](https://img.shields.io/badge/Citations-612-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/ML-KULeuven/deepproblog)![GitHub stars](https://img.shields.io/github/stars/ML-KULeuven/deepproblog.svg?logo=github&label=Stars)| +|NIPS 2018|DeepProbLog: Neural Probabilistic Logic Programming|KU Leuven| [[paper]](https://arxiv.org/pdf/1805.10872.pdf)![Scholar citations](https://img.shields.io/badge/Citations-613-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/ML-KULeuven/deepproblog)![GitHub stars](https://img.shields.io/github/stars/ML-KULeuven/deepproblog.svg?logo=github&label=Stars)| |ICML 2022|Injecting Logical Constraints into Neural Networks via Straight-Through Estimators|Arizona State University| [[paper]](https://arxiv.org/pdf/2307.04347.pdf)![Scholar citations](https://img.shields.io/badge/Citations-22-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/azreasoners/cl-ste)![GitHub stars](https://img.shields.io/github/stars/azreasoners/cl-ste.svg?logo=github&label=Stars)| ### Concept bottleneck models | Venue | Title | Affiliation |       Link       |   Source   | | :---: | :---: | :---------: | :---: | :----: | -|ICML 2020|Concept Bottleneck Models|Standard University| [[paper]](https://arxiv.org/pdf/2007.04612.pdf)![Scholar citations](https://img.shields.io/badge/Citations-732-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/yewsiang/ConceptBottleneck)![GitHub stars](https://img.shields.io/github/stars/yewsiang/ConceptBottleneck.svg?logo=github&label=Stars)| -|ICLR 2023|POST-HOC CONCEPT BOTTLENECK MODELS|Standard University| [[paper]](https://arxiv.org/pdf/2205.15480.pdf)![Scholar citations](https://img.shields.io/badge/Citations-159-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/mertyg/post-hoc-cbm)![GitHub stars](https://img.shields.io/github/stars/mertyg/post-hoc-cbm.svg?logo=github&label=Stars)| +|ICML 2020|Concept Bottleneck Models|Standard University| [[paper]](https://arxiv.org/pdf/2007.04612.pdf)![Scholar citations](https://img.shields.io/badge/Citations-736-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/yewsiang/ConceptBottleneck)![GitHub stars](https://img.shields.io/github/stars/yewsiang/ConceptBottleneck.svg?logo=github&label=Stars)| +|ICLR 2023|POST-HOC CONCEPT BOTTLENECK MODELS|Standard University| [[paper]](https://arxiv.org/pdf/2205.15480.pdf)![Scholar citations](https://img.shields.io/badge/Citations-160-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/mertyg/post-hoc-cbm)![GitHub stars](https://img.shields.io/github/stars/mertyg/post-hoc-cbm.svg?logo=github&label=Stars)| |ICML 2023|Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat|BU| [[paper]](https://arxiv.org/pdf/2307.05350.pdf)![Scholar citations](https://img.shields.io/badge/Citations-7-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/batmanlab/ICML-2023-Route-interpret-repeat)![GitHub stars](https://img.shields.io/github/stars/batmanlab/ICML-2023-Route-interpret-repeat.svg?logo=github&label=Stars)| |CVPR 2023|Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification|UPENN| [[paper]](https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Language_in_a_Bottle_Language_Model_Guided_Concept_Bottlenecks_for_CVPR_2023_paper.pdf)![Scholar citations](https://img.shields.io/badge/Citations-143-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/YueYANG1996/LaBo)![GitHub stars](https://img.shields.io/github/stars/YueYANG1996/LaBo.svg?logo=github&label=Stars)| |ICLR 2023|Label-free Concept Bottleneck Models|UCSD| [[paper]](https://openreview.net/pdf?id=FlCg47MNvBA)![Scholar citations](https://img.shields.io/badge/Citations-105-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/Trustworthy-ML-Lab/Label-free-CBM)![GitHub stars](https://img.shields.io/github/stars/Trustworthy-ML-Lab/Label-free-CBM.svg?logo=github&label=Stars)| |AAAI 2023|Interactive Concept Bottleneck Models|Google| [[paper]](https://arxiv.org/pdf/2212.07430.pdf)![Scholar citations](https://img.shields.io/badge/Citations-41-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/google-research/google-research/tree/master/interactive_cbms)| |NIPS 2022|Addressing Leakage in Concept Bottleneck Models|Harvard University| [[paper]](https://finale.seas.harvard.edu/sites/scholar.harvard.edu/files/finale/files/10494_addressing_leakage_in_concept_.pdf)![Scholar citations](https://img.shields.io/badge/Citations-50-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/dtak/addressing-leakage)![GitHub stars](https://img.shields.io/github/stars/dtak/addressing-leakage.svg?logo=github&label=Stars)| -|ICML 2021|Promises and Pitfalls of Black-Box Concept Learning Models|Harvard University| [[paper]](https://arxiv.org/pdf/2106.13314.pdf)![Scholar citations](https://img.shields.io/badge/Citations-80-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)|| +|ICML 2021|Promises and Pitfalls of Black-Box Concept Learning Models|Harvard University| [[paper]](https://arxiv.org/pdf/2106.13314.pdf)![Scholar citations](https://img.shields.io/badge/Citations-81-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)|| |ICML 2018|Interpretability Beyond Feature Attribution:Quantitative Testing with Concept Activation Vectors (TCAV)|Google| [[paper]](https://arxiv.org/pdf/1711.11279.pdf)![Scholar citations](https://img.shields.io/badge/Citations-2.0k-_.svg?logo=google-scholar&labelColor=4f4f4f&color=3388ee)| [[code]](https://github.com/tensorflow/tcav)![GitHub stars](https://img.shields.io/github/stars/tensorflow/tcav.svg?logo=github&label=Stars)| ### Model Editing | Venue | Title | Affiliation |       Link       |   Source   |