Speeding up LIME using Attention Weights
Authors: 
Sudarsun Santhiappan, Mukesh Kumar Reghu, Mahendran Saminathan, Aakash VeerappanAuthors Info & Claims
Pages 444 - 448
Abstract
LIME (Local Interpretable Model-Agnostic Explanations), a model-agnostic framework for eXplainable AI (XAI), has emerged as a powerful technique for generating instance-level explanations. However, the computational cost of LIME can be prohibitively high, especially while dealing with large datasets or complex models. This work proposes a novel approach to speed up the LIME algorithm by leveraging attention weights from an upstream classification task. The per-label attention mechanism allows a classification model to focus on different labels independently and learn label-specific attention weights. By utilizing the attention weights of a target label, we aim to restrict the perturbable tokens, thereby reducing the number of perturbations and inference time required by LIME. Experiments on open-source datasets demonstrate a minimum 50% speed improvement in explanation generation, preserving over 85% of LIME’s original explanations.
References
[1]
Eva Gibaja and Sebastián Ventura. 2015. A Tutorial on Multilabel Learning. ACM Comput. Surv. 47, 3, Article 52 (apr 2015), 38 pages. https://doi.org/10.1145/2716262
[2]
Andreas Holzinger, Randy Goebel, Ruth Fong, Taesup Moon, Klaus-Robert Müller, and Wojciech Samek. 2020. XxAI - Beyond Explainable Artificial Intelligence. In XxAI - Beyond Explainable AI: International Workshop, Held in Conjunction with ICML 2020, July 18, 2020, Vienna, Austria, Revised and Extended Papers (Vienna, Austria). Springer-Verlag, Berlin, Heidelberg, 3–10. https://doi.org/10.1007/978-3-031-04083-2_1
[3]
Alistair E.W. Johnson, Tom J. Pollard, Lu Shen, Li wei H. Lehman, Mohammad Ghassemi Mengling Feng, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G. Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific Data (2016). https://doi.org/10.1038/sdata.2016.35
[4]
Hamid Karimi, Tyler Derr, and Jiliang Tang. 2019. Characterizing the Decision Boundary of Deep Neural Networks. CoRR abs/1912.11460 (2019). arXiv:1912.11460http://arxiv.org/abs/1912.11460
[5]
Scott M. Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems (Long Beach, California, USA) (NIPS’17). Curran Associates Inc., Red Hook, NY, USA, 4768–4777.
[6]
James Mullenbach, Sarah Wiegreffe, Jon Duke, Jimeng Sun, and Jacob Eisenstein. 2018. Explainable Prediction of Medical Codes from Clinical Text. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Association for Computational Linguistics, New Orleans, Louisiana, 1101–1111. https://doi.org/10.18653/v1/N18-1100
[7]
Jinseok Nam, Jungi Kim, Eneldo Loza Mencía, Iryna Gurevych, and Johannes Fürnkranz. 2014. Large-Scale Multi-Label Text Classification — Revisiting Neural Networks. In Machine Learning and Knowledge Discovery in Databases (Nancy France). Springer-Verlag, Berlin, Heidelberg, 437–452. https://doi.org/10.1007/978-3-662-44851-9_28
[8]
Lutz Prechelt. 2012. Early Stopping — But When?Springer Berlin Heidelberg, Berlin, Heidelberg, 53–67. https://doi.org/10.1007/978-3-642-35289-8_5
[9]
Saeed Mian Qaisar. 2020. Sentiment Analysis of IMDb Movie Reviews Using Long Short-Term Memory. In 2020 2nd International Conference on Computer and Information Sciences (ICCIS). 1–4. https://doi.org/10.1109/ICCIS49240.2020.9257657
[10]
Ning Qian. 1999. On the momentum term in gradient descent learning algorithms. Neural Networks 12, 1 (1999), 145–151. https://doi.org/10.1016/S0893-6080(98)00116-6
[11]
Vineet Raina and Srinath Krishnamurthy. 2022. Natural Language Processing. 63–73. https://doi.org/10.1007/978-1-4842-7419-4_6
[12]
Marco Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations. Association for Computational Linguistics, San Diego, California, 97–101. https://doi.org/10.18653/v1/N16-3020
[13]
Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Anchors: High-Precision Model-Agnostic Explanations. Proceedings of the AAAI Conference on Artificial Intelligence 32, 1 (Apr. 2018). https://doi.org/10.1609/aaai.v32i1.11491
[14]
Cedric Schockaert, Vadim Macher, and Alexander Schmitz. 2020. VAE-LIME: Deep Generative Model Based Approach for Local Data-Driven Model Interpretability Applied to the Ironmaking Industry. https://doi.org/10.13140/RG.2.2.15447.70567
[15]
Sheng Shi, Yangzhou Du, and Wei Fan. 2020. An Extension of LIME with Improvement of Interpretability and Fidelity. CoRR abs/2004.12277 (2020). arXiv:2004.12277https://arxiv.org/abs/2004.12277
[16]
Kacper Sokol and Peter A. Flach. 2020. LIMEtree: Interactively Customisable Explanations Based on Local Surrogate Multi-output Regression Trees. CoRR abs/2005.01427 (2020).
[17]
Elena Solovyeva and Ali Abdullah. 2021. Binary and Multiclass Text Classification by Means of Separable Convolutional Neural Network. Inventions 6, 4 (2021). https://doi.org/10.3390/inventions6040070
[18]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. CoRR abs/1706.03762 (2017). arXiv:1706.03762http://arxiv.org/abs/1706.03762
[19]
Hongxin Wei, Renchunzi Xie, Hao Cheng, Lei Feng, Bo An, and Yixuan Li. 2022. Mitigating Neural Network Overconfidence with Logit Normalization. In Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 23631–23644. https://proceedings.mlr.press/v162/wei22d.html
[20]
Sarah Wiegreffe and Yuval Pinter. 2019. Attention is not Explanation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 11–20. https://doi.org/10.18653/v1/D19-1002
Index Terms
- Speeding up LIME using Attention Weights
Recommendations
Multi-task Attention-Based Semi-supervised Learning for Medical Image Segmentation
Medical Image Computing and Computer Assisted Intervention – MICCAI 2019AbstractWe propose a novel semi-supervised image segmentation method that simultaneously optimizes a supervised segmentation and an unsupervised reconstruction objectives. The reconstruction objective uses an attention mechanism that separates the ...
Explanation vs. attention: A two-player game to obtain attention for VQA and visual dialog
Highlights- We propose a means for obtaining surrogate supervision for obtaining better attention maps based on the visual explanation in the form of Grad-CAM results.
AbstractIn this paper, we aim to obtain improved attention for a visual question answering (VQA) task. It is challenging to provide supervision for attention. An observation we make is that visual explanations as obtained through class ...
Co-attention network with label embedding for text classification
AbstractMost existing methods for text classification focus on extracting a highly discriminative text representation, which, however, is typically computationally inefficient. To alleviate this issue, label embedding frameworks are proposed ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
January 2024
627 pages
ISBN:9798400716348
DOI:10.1145/3632410
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 04 January 2024
Check for updates
Author Tags
Qualifiers
- Short-paper
- Research
- Refereed limited
Conference
CODS-COMAD 2024
CODS-COMAD 2024: 7th Joint International Conference on Data Science & Management of Data (11th ACM IKDD CODS and 29th COMAD)
January 4 - 7, 2024
Bangalore, India
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 69Total Downloads
- Downloads (Last 12 months)69
- Downloads (Last 6 weeks)4
Reflects downloads up to 04 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format