Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/iCGY96/awesome_concept_learning_list

A curated list of papers & resources linked to concept learning
https://github.com/iCGY96/awesome_concept_learning_list

List: awesome_concept_learning_list

Last synced: 16 days ago
JSON representation

A curated list of papers & resources linked to concept learning

Awesome Lists containing this project

README 

        
# Awesome-Concept-Learning 



Concepts are complex, and often time contains abstract information to be distilled from real-world data. The problem of learning concepts in a complex and dynamic environment is essential to accomplish complex real-world missions. This topic has plausible real-world applications and is gathering much attention in the research community.



Here, we provide a non-exhaustive list of papers that study concept learning.



## Preprints

- Uncovering Unique Concept Vectors through Latent Space Decomposition [[paper]](https://arxiv.org/abs/2307.06913) 

- Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification [[paper]](https://arxiv.org/abs/2307.04343) 

- SHARCS: Shared Concept Space for Explainable Multimodal Learning [[paper]](https://arxiv.org/abs/2307.00316) 

- A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation [[paper]](https://arxiv.org/abs/2306.07304) 

- ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models [[paper]](https://arxiv.org/abs/2306.04695) [[code]](https://github.com/conceptbed/evaluations)

- Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models [[paper]](https://arxiv.org/abs/2305.18292)

- Concept Decomposition for Visual Exploration and Inspiration [[paper]](https://arxiv.org/abs/2305.18203)

- Explain Any Concept: Segment Anything Meets Concept-Based Explanation [[paper]](https://arxiv.org/abs/2305.10289)

- Causal Proxy Models for Concept-Based Model Explanations [[paper]](https://arxiv.org/abs/2209.14279) [[code]](https://github.com/frankaging/Causal-Proxy-Model)

- ConceptLab: Creative Generation using Diffusion Prior Constraints [[paper]](https://arxiv.org/abs/2308.02669) [[code]](https://github.com/kfirgoldberg/ConceptLab)



## 2023

- Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models (**ICCV** 2023) [[paper]](https://arxiv.org/abs/2306.05357) [[code]](https://github.com/nanlliu/Unsupervised-Compositional-Concepts-Discovery)

- Probabilistic Concept Bottleneck Models (**ICML** 2023) [[paper]](https://arxiv.org/abs/2306.01574) [[code]](https://github.com/ejkim47/prob-cbm)

- Text-To-Concept (and Back) via Cross-Model Alignment (**ICML** 2023) [[paper]](https://arxiv.org/abs/2305.06386)

- Discover and Cure: Concept-aware Mitigation of Spurious Correlation (**ICML** 2023) [[paper]](https://arxiv.org/abs/2305.00650) [[code]](https://github.com/wuyxin/disc)

- Interpretable Neural-Symbolic Concept Reasoning (**ICML** 2023) [[paper]](https://arxiv.org/abs/2304.14068) [[code]](https://github.com/pietrobarbiero/pytorch_explain)

- Cones: Concept Neurons in Diffusion Models for Customized Generation (**ICML** 2023) [[paper]](https://arxiv.org/abs/2303.05125) [[code]](https://github.com/johanan528/cones)

- A Closer Look at the Intervention Procedure of Concept Bottleneck Models (**ICML** 2023) [[paper]](https://arxiv.org/abs/2302.14260) [[code]](https://github.com/ssbin4/closer-intervention-cbm)

- Learning Bottleneck Concepts in Image Classification (**CVPR** 2023) [[paper]](https://github.com/wbw520/botcl) [[code]](https://arxiv.org/abs/2304.10131)

- Dynamic Conceptional Contrastive Learning for Generalized Category Discovery (**CVPR** 2023) [[paper]](https://arxiv.org/abs/2303.17393) [[code]](https://github.com/tpcd/dccl)

- Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification (**CVPR** 2023) [[paper]](https://arxiv.org/abs/2211.11158) [[code]](https://github.com/yueyang1996/labo)

- Label-Free Concept Bottleneck Models (**ICLR** 2023) [[paper]](https://arxiv.org/abs/2304.06129) [[code]](https://github.com/Trustworthy-ML-Lab/Label-free-CBM)

- Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation (**AAAI** 2023) [[paper]](https://arxiv.org/abs/2302.06072) 

- Towards Robust Metrics for Concept Representation Evaluation (**AAAI** 2023) [[paper]](https://arxiv.org/abs/2301.10367) 

- Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees (**TMLR** 2023) [[paper]](https://arxiv.org/abs/2301.11911) [[code]](https://github.com/jvielhaben/mcd-xai)



## 2022

- Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off (**NeurIPS** 2022) [[paper]](https://arxiv.org/abs/2209.09056) [[code]](https://github.com/pietrobarbiero/pytorch_explain)

- ZeroC: A Neuro-Symbolic Model for Zero-shot Concept Recognition and Acquisition at Inference Time (**NeurIPS** 2022) [[paper]](https://arxiv.org/abs/2206.15049) [[code]](https://github.com/snap-stanford/zeroc)

- Interactive Disentanglement: Learning Concepts by Interacting with their Prototype Representations (**CVPR** 2022) [[paper]](https://arxiv.org/abs/2112.02290) [[code]](https://github.com/ml-research/xiconceptlearning)

- Concept Learning for Interpretable Multi-Agent Reinforcement Learning (**CoRL** 2022) [[paper]](https://arxiv.org/abs/2302.12232)



## 2021

- Unsupervised Learning of Compositional Energy Concepts (**NeurIPS** 2021) [[paper]](https://arxiv.org/abs/2111.03042) [[code]](https://github.com/yilundu/comet)



## 2020

- Concept Bottleneck Models (**ICML** 2020) [[paper]](https://arxiv.org/abs/2007.04612) [[code]](https://github.com/yewsiang/ConceptBottleneck)



## 2017

- ConceptNet 5.5: An Open Multilingual Graph of General Knowledge (**AAAI** 2017) [[paper]](https://arxiv.org/abs/1612.03975) [[code]](https://github.com/commonsense/conceptnet-numberbatch)



## 2016

- beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework (**ICLR** 2016) [[paper]](https://arxiv.org/abs/1612.03975) [[code]](https://github.com/commonsense/conceptnet-numberbatch)



## 2015

- Human-level concept learning through probabilistic program induction (**Science** 2015) [[paper]](https://openreview.net/forum?id=Sy2fzU9gl)



### Contributing

Please help us improve the above listing by submitting PRs of other papers in this space. Thank you!