{"type":"ScholarlyArticle","title":"DeLELSTM: Decomposition-based Linear Explainable LSTM to Capture Instantaneous and Long-term Effects in Time Series","authors":[{"name":"Chaoqun Wang","slug":"chaoqun-wang","given":"Chaoqun","family":"Wang","affiliation":"School of Data Science , City University of Hong Kong , Hong Kong , China"},{"name":"Yijun Li","slug":"yijun-li","given":"Yijun","family":"Li","affiliation":"School of Data Science , City University of Hong Kong , Hong Kong , China"},{"name":"Xiangqian Sun","slug":"xiangqian-sun","given":"Xiangqian","family":"Sun","affiliation":"School of Data Science , City University of Hong Kong , Hong Kong , China"},{"name":"Qi Wu","slug":"qi-wu","given":"Qi","family":"Wu","affiliation":"School of Data Science , City University of Hong Kong , Hong Kong , China"},{"name":"Dongdong Wang","slug":"dongdong-wang","given":"Dongdong","family":"Wang","affiliation":"JD Digits , Beijing , China"},{"name":"Zhixiang Huang","slug":"zhixiang-huang","given":"Zhixiang","family":"Huang","affiliation":"JD Digits , Beijing , China"}],"abstract":"Time series forecasting is prevalent in various real-world applications. Despite the promising results of deep learning models in time series forecasting, especially the Recurrent Neural Networks (RNNs), the explanations of time series models, which are critical in high-stakes applications, have received little attention. In this paper, we propose a Decomposition-based Linear Explainable LSTM (DeLELSTM) to improve the interpretability of LSTM. Conventionally, the interpretability of RNNs only concentrates on the variable importance and time importance. We additionally distinguish between the instantaneous influence of new coming data and the long-term effects of historical data. Specifically, DeLELSTM consists of two components, i.e., standard LSTM and tensorized LSTM. The tensorized LSTM assigns each variable with a unique hidden state making up a matrix h(t), and the standard LSTM models all the variables with a shared hidden state H(t). By decomposing the H(t) into the linear combination of past information h(t-1) and the fresh information h(t)-h(t-1), we can get the instantaneous influence and the long-term effect of each feature. In addition, the advantage of linear regression also makes the explanation transparent and clear. We demonstrate the effectiveness and interpretability of DeLELSTM on three empirical datasets. Extensive experiments show that the proposed method achieves competitive performance against the baseline methods and provides a reliable explanation relative to domain knowledge.","doi":"10.24963/ijcai.2023/478","url":"https://ijcai.org/proceedings/2023/478","pdf":"https://ijcai.org/proceedings/2023/0478.pdf","markdown":"https://ijcai.org/proceedings/2023/478.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/478","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Machine Learning","track":"Main Track","number":478,"pages":{"first":4299,"last":4307},"keywords":["Machine Learning: ML: Time series and data streams","Machine Learning: ML: Explainable/Interpretable machine learning"],"videos":[],"references":[{"position":1,"raw":"[Ancona et al., 2017] Marco Ancona, Enea Ceolini, Cengiz Öztireli, and Markus Gross. Towards better understand- ing of gradient-based attribution methods for deep neural networks. arXiv preprint arXiv:1711.06104, 2017.","title":"Towards better understanding of gradient-based attribution methods for deep neural networks","authors":"Marco Ancona, Enea Ceolini, Cengiz Öztireli, Markus Gross","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chakraborty et al., 2012] Prithwish Chakraborty, Manish Marwah, Martin Arlitt, and Naren Ramakrishnan. Fine- grained photovoltaic output prediction using a bayesian ensemble. In Proceedings of the AAAI Conference on Ar- tificial Intelligence, volume 26, pages 274-280, 2012.","title":"Finegrained photovoltaic output prediction using a bayesian ensemble","authors":"Chakraborty","year":"2012","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Choi et al., 2016] Edward Choi, Mohammad Taha Ba- hadori, Jimeng Sun, Joshua Kulas, Andy Schuetz, and Walter Stewart. Retain: An interpretable predictive model for healthcare using reverse time attention mechanism. Advances in neural information processing systems, 29, 2016.","title":"Retain: An interpretable predictive model for healthcare using reverse time attention mechanism","authors":"Edward Choi, Mohammad Taha Bahadori, Jimeng Sun, Joshua Kulas, Andy Schuetz, Walter Stewart","year":"2016","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Dabkowski and Gal, 2017] Piotr Dabkowski and Yarin Gal. Real time image saliency for black box classifiers. Ad- vances in neural information processing systems, 30, 2017.","title":"Real time image saliency for black box classifiers","authors":"Piotr Dabkowski, Yarin Gal","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ding et al., 2022] Weiping Ding, Mohamed Abdel-Basset, Hossam Hawash, and Ahmed M Ali. Explainability of ar- tificial intelligence methods, applications and challenges: A comprehensive survey. Information Sciences, 2022.","title":"Explainability of artificial intelligence methods, applications and challenges: A comprehensive survey","authors":"Weiping Ding, Mohamed Abdel-Basset, Hossam Hawash, Ahmed M Ali","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fong and Vedaldi, 2017] Ruth C Fong and Andrea Vedaldi. Interpretable explanations of black boxes by meaningful perturbation. In Proceedings of the IEEE international conference on computer vision, pages 3429-3437, 2017.","title":"Interpretable explanations of black boxes by meaningful perturbation","authors":"C Ruth, Andrea Fong, Vedaldi","year":"2017","venue":"Proceedings of the IEEE international conference on computer vision","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Franklin et al., 2008] Meredith Franklin, Petros Koutrakis, and Joel Schwartz. The role of particle composition on the association between pm2. 5 and mortality. Epidemiology (Cambridge, Mass.), 19(5):680, 2008.","title":"The role of particle composition on the association between pm2. 5 and mortality","authors":"Meredith Franklin, Petros Koutrakis, Joel Schwartz","year":"2008","venue":"Epidemiology","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gao et al., 2022] Penglei Gao, Xi Yang, Kaizhu Huang, Rui Zhang, and John Yannis Goulermas. Explainable ten- sorized neural ordinary differential equations for arbitrary- step time series prediction. IEEE Transactions on Knowl- edge and Data Engineering, 2022.","title":"Explainable tensorized neural ordinary differential equations for arbitrarystep time series prediction","authors":"Gao","year":"2022","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Guo et al., 2019] Tian Guo, Tao Lin, and Nino Antulov- Fantulin. Exploring interpretable lstm neural networks over multi-variable data. In International conference on machine learning, pages 2494-2504. PMLR, 2019.","title":"Exploring interpretable lstm neural networks over multi-variable data","authors":"Tian Guo, Tao Lin, Nino Antulov-Fantulin","year":"2019","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[He et al., 2017] Zhen He, Shaobing Gao, Liang Xiao, Daxue Liu, Hangen He, and David Barber. Wider and deeper, cheaper and faster: Tensorized lstms for sequence learning. Advances in neural information processing sys- tems, 30, 2017.","title":"Wider and deeper, cheaper and faster: Tensorized lstms for sequence learning","authors":"Zhen He, Shaobing Gao, Liang Xiao, Daxue Liu, Hangen He, David Barber","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hochreiter and Schmidhuber, 1997] Sepp Hochreiter and Jürgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"Schmidhuber Hochreiter, Sepp Hochreiter, Jürgen Schmidhuber","year":"1997","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hsieh et al., 2021] Tsung-Yu Hsieh, Suhang Wang, Yiwei Sun, and Vasant Honavar. Explainable multivariate time series classification: a deep neural network which learns to attend to important variables as well as time intervals. In Proceedings of the 14th ACM international conference on web search and data mining, pages 607-615, 2021.","title":"Explainable multivariate time series classification: a deep neural network which learns to attend to important variables as well as time intervals","authors":"Tsung-Yu Hsieh, Suhang Wang, Yiwei Sun, Vasant Honavar","year":"2021","venue":"Proceedings of the 14th ACM international conference on web search and data mining","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Jain and Wallace, 2019] Sarthak Jain and Byron C Wal- lace. Attention is not explanation. arXiv preprint arXiv:1902.10186, 2019.","title":"Attention is not explanation","authors":"Sarthak Jain, Byron C Wallace","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kingma and Ba, 2014] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lai et al., 2018] Guokun Lai, Wei-Cheng Chang, Yiming Yang, and Hanxiao Liu. Modeling long-and short-term temporal patterns with deep neural networks. In The 41st international ACM SIGIR conference on research & devel- opment in information retrieval, pages 95-104, 2018.","title":"Modeling long-and short-term temporal patterns with deep neural networks","authors":"Lai","year":"2018","venue":"The 41st international ACM SIGIR conference on research & development in information retrieval","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Liang et al., 2015] Xuan Liang, Tao Zou, Bin Guo, Shuo Li, Haozhe Zhang, Shuyi Zhang, Hui Huang, and Song Xi Chen. Assessing beijing's pm2. 5 pollution: severity, weather impact, apec and winter heating. Proceedings of the Royal Society A: Mathematical, Physical and En- gineering Sciences, 471(2182):20150257, 2015.","title":"Assessing beijing's pm2. 5 pollution: severity, weather impact, apec and winter heating","authors":"Xuan Liang, Tao Zou, Bin Guo, Shuo Li, Haozhe Zhang, Shuyi Zhang, Hui Huang, Song Xi, Chen","year":"2015","venue":"Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Masoomi et al., 2021] Aria Masoomi, Davin Hill, Zhonghui Xu, Craig P Hersh, Edwin K Silverman, Peter J Castaldi, Stratis Ioannidis, and Jennifer Dy. Expla- nations of black-box models based on directional feature interactions. In International Conference on Learning Representations, 2021.","title":"Explanations of black-box models based on directional feature interactions","authors":"Masoomi","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Mohankumar et al., 2020] Akash Kumar Mohankumar, Preksha Nema, Sharan Narasimhan, Mitesh M Khapra, Balaji Vasan Srinivasan, and Balaraman Ravindran. Towards transparent and explainable attention models. arXiv preprint arXiv:2004.14243, 2020.","title":"Towards transparent and explainable attention models","authors":"Akash Kumar Mohankumar, Preksha Nema, Sharan Narasimhan, M Mitesh, Balaji Khapra, Balaraman Vasan Srinivasan, Ravindran","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pu et al., 2011] Wei-wei Pu, Xiu-juan Zhao, Xiao-ling Zhang, and Zhi-qiang Ma. Effect of meteorological factors on pm2. 5 during july to september of beijing. Procedia Earth and Planetary Science, 2:272-277, 2011.","title":"Effect of meteorological factors on pm2. 5 during july to september of beijing","authors":"Wei-Wei Pu, Xiu-Juan Zhao, Xiao-Ling Zhang, Zhi-Qiang Ma","year":"2011","venue":"Procedia Earth and Planetary Science","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Rigotti et al., 2021] Mattia Rigotti, Christoph Miksovic, Ioana Giurgiu, Thomas Gschwind, and Paolo Scotton. Attention-based interpretability with concept transform- ers. In International Conference on Learning Represen- tations, 2021.","title":"Attention-based interpretability with concept transformers","authors":"Mattia Rigotti, Christoph Miksovic, Ioana Giurgiu, Thomas Gschwind, Paolo Scotton","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rojat et al., 2021] Thomas Rojat, Raphaël Puget, David Filliat, Javier Del Ser, Rodolphe Gelin, and Na- talia Díaz-Rodríguez. Explainable artificial intelligence (xai) on timeseries data: A survey. arXiv preprint arXiv:2104.00950, 2021.","title":"Explainable artificial intelligence (xai) on timeseries data: A survey","authors":"Thomas Rojat, Raphaël Puget, David Filliat, Javier Del Ser, Rodolphe Gelin","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Serrano and Smith, 2019] Sofia Serrano and Noah A Smith. Is attention interpretable? arXiv preprint arXiv:1906.03731, 2019.","title":"Is attention interpretable","authors":"Smith ; Serrano, Sofia Serrano, Noah A Smith","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Shrikumar et al., 2017] Avanti Shrikumar, Peyton Green- side, and Anshul Kundaje. Learning important features through propagating activation differences. In Interna- tional conference on machine learning, pages 3145-3153.","title":"Avanti Shrikumar, Peyton Greenside, and Anshul Kundaje. Learning important features through propagating activation differences","authors":"Shrikumar","year":"2017","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"PMLR, 2017.","title":null,"authors":"Pmlr","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sun et al., 2021] Xiaofei Sun, Diyi Yang, Xiaoya Li, Tian- wei Zhang, Yuxian Meng, Han Qiu, Guoyin Wang, Ed- uard Hovy, and Jiwei Li. Interpreting deep learning models in natural language processing: A review. arXiv preprint arXiv:2110.10470, 2021.","title":"Interpreting deep learning models in natural language processing: A review","authors":"Xiaofei Sun, Diyi Yang, Xiaoya Li, Tianwei Zhang, Yuxian Meng, Han Qiu, Guoyin Wang, Eduard Hovy, Jiwei Li","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Sundararajan et al., 2017] Mukund Sundararajan, Ankur Taly, and Qiqi Yan. Axiomatic attribution for deep net- works. In International conference on machine learning, pages 3319-3328. PMLR, 2017.","title":"Axiomatic attribution for deep networks","authors":"Mukund Sundararajan, Ankur Taly, Qiqi Yan","year":"2017","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Tonekaboni et al., 2020] Sana Tonekaboni, Shalmali Joshi, Kieran Campbell, David K Duvenaud, and Anna Golden- berg. What went wrong and when? instance-wise feature importance for time-series black-box models. Advances in Neural Information Processing Systems, 33:799-809, 2020.","title":"What went wrong and when? instance-wise feature importance for time-series black-box models","authors":"Sana Tonekaboni, Shalmali Joshi, Kieran Campbell, David K Duvenaud, Anna Goldenberg","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Tsang et al., 2020] Michael Tsang, Sirisha Rambhatla, and Yan Liu. How does this interaction affect me? inter- pretable attribution for feature interactions. Advances in neural information processing systems, 33:6147-6159, 2020.","title":"How does this interaction affect me? interpretable attribution for feature interactions","authors":"Michael Tsang, Sirisha Rambhatla, Yan Liu","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wang et al., 2020] Jian Qi Wang, Yu Du, and Jing Wang. Lstm based long-term energy consumption prediction with periodicity. Energy, 197:117197, 2020.","title":"Lstm based long-term energy consumption prediction with periodicity","authors":"Jian Qi, Wang, Yu Du, Jing Wang","year":"2020","venue":"Energy","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wu et al., 2013] Yue Wu, José Miguel Hernández-Lobato, and Ghahramani Zoubin. Dynamic covariance models for multivariate financial time series. In International Confer- ence on Machine Learning, pages 558-566. PMLR, 2013.","title":"Dynamic covariance models for multivariate financial time series","authors":"Yue Wu, José Miguel Hernández-Lobato, Ghahramani Zoubin","year":"2013","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Yang et al., 2018] Yinchong Yang, Volker Tresp, Marius Wunderle, and Peter A Fasching. Explaining therapy predictions with layer-wise relevance propagation in neu- ral networks. In 2018 IEEE International Conference on Healthcare Informatics (ICHI), pages 152-162. IEEE, 2018.","title":"Explaining therapy predictions with layer-wise relevance propagation in neural networks","authors":"Yang","year":"2018","venue":"IEEE International Conference on Healthcare Informatics (ICHI)","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhang, 2019] Yuan Zhang. Attain: Attention-based time- aware lstm networks for disease progression modeling. In In Proceedings of the 28th International Joint Con- ference on Artificial Intelligence (IJCAI-2019), pp. 4369- 4375, Macao, China., 2019.","title":"Attain: Attention-based timeaware lstm networks for disease progression modeling","authors":"Yuan Zhang","year":"2019","venue":"Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-2019)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}