Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Cognitive Computation
Published in:

04-11-2023

Machine Un-learning: An Overview of Techniques, Applications, and Future Directions

Authors: Siva Sai, Uday Mittal, Vinay Chamola, Kaizhu Huang, Indro Spinelli, Simone Scardapane, Zhiyuan Tan, Amir Hussain

Published in: Cognitive Computation | Issue 2/2024

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

ML applications proliferate across various sectors. Large internet firms employ ML to train intelligent models using vast datasets, including sensitive user information. However, new regulations like GDPR require data removal by businesses. Deleting data from ML models is more complex than databases. Machine Un-learning (MUL), an emerging field, garners academic interest for selectively erasing learned data from ML models. MUL benefits multiple disciplines, enhancing privacy, security, usability, and accuracy. This article reviews MUL’s significance, providing a taxonomy and summarizing key MUL algorithms. We categorize modern MUL models by criteria, including model independence, data driven, and implementation considerations. We explore MUL applications in smart devices and recommendation systems. We also identify open questions and future research areas. This work advances methods for implementing regulations like GDPR and safeguarding user privacy.
previous article State-of-the-Art of Stress Prediction from Heart Rate Variability Using Artificial Intelligence
next article Graph-Based Interactive Matching for Pairs of News Articles

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
Literature
1.
Goldsteen A, Ezov G, Shmelkin R, Moffie M, Farkash A. Data minimization for gdpr compliance in machine learning models. AI and Ethics. 2021;1–15.
2.
Mourby M, Cathaoir KO´, Collin CB. Transparency of machine-learning in healthcare: The gdpr & european health law. Comput Law Secur Rev. 2021;43:105611.
3.
4.
5.
6.
Voigt P, Von A, dem Bussche, The EU general data protection regulation (gdpr), A Practical Guide, 1st Ed., Cham: Springer Inter- national Publishing. 2017;10(3152676):10–5555.
7.
Strobel M, Aspects of transparency in machine learning, in Proceed- ings of the 18th International Conference on Autonomous Agents and MultiAgent Systems. 2019;2449–2451.
8.
Lu¨ L, Medo M, Yeung CH, Zhang Y-C, Zhang Z-K, Zhou T. Recommender systems. Phys Rep. 2012;519(1):1–49.
9.
Resnick P, Varian HR. Recommender systems. Communica- tions of the ACM. 1997;40(3):56–8.CrossRef
10.
Kaelbling LP, Littman ML, Moore AW. Reinforcement learning: a survey. J Art Intell Res. 1996;4:237–85.
11.
12.
Westin AF. Privacy and freedom. Washington and Lee Law Rev. 1968;25(1):166.
13.
Jordan PW. An introduction to usability. Crc Press. 1998.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
Ayyagari R. An exploratory analysis of data breaches from 2005–2011: trends and insights. J Inf Priv Secur. 2012;8(2):33–56.
24.
Li Y, Liu Q. A comprehensive review study of cyber-attacks and cyber security; emerging trends and recent developments. Energy Rep. 2021;7:8176–86.CrossRef
25.
Sethuraman SC, Vijayakumar V, Walczak S. Cyber attacks on healthcare devices using unmanned aerial vehicles. J Med Syst. 2020;44(1):29.CrossRef
26.
27.
Mehrabi N, Morstatter F, Saxena N, Lerman K, Galstyan A. A survey on bias and fairness in machine learning. ACM Computing Surveys (CSUR). 2021;54(6):1–35.CrossRef
28.
29.
30.
Grover H, Alladi T, Chamola V, Singh D, Choo KK. Edge computing and deep learning enabled secure multitier network for internet of vehicles. IEEE Internet Things J. 2021;8(19):14787–14796.
31.
Zhou Z-H, Machine learning. Springer Nature. 2021.
32.
Mitchell TM, et al. Machine learning. McGraw-hill New York. 2007;1.
33.
El Naqa I, Murphy MJ. What is machine learning? Springer. 2015.
34.
Bottou L. Stochastic gradient descent tricks. Neural Networks: Tricks of the Trade: Second Edition. 2012;421–436.
35.
36.
Gupta V, Jung C, Neel S, Roth A, Sharifi-Malvajerdi S, Waites C. Adaptive machine unlearning. Adv Neural Inf Process Sys. 2021;34:16319–16 330.
37.
38.
Melnikov Y. Influence functions and matrices. CRC Press. 1998;119.
39.
Ketkar N, Ketkar N. Stochastic gradient descent. Deep learning with Python: a hands-on introduction. 2017;113–132.
40.
Tahiliani A, Hassija V, Chamola V, Guizani M. Machine unlearning: its need and implementation strategies, in 2021 Thirteenth International Conference on Contemporary Computing (IC3–2021), ser. IC3 ’21. New York, NY, USA: association for computing machinery. 2021;241–246. [Online]. Available: https://​doi.​org/​10.​1145/​3474124.​3474158.
41.
Sekhari A, Acharya J, Kamath G, Suresh AT. Remember what you want to forget: algorithms for machine unlearning. Advances in Neural Information Processing Systems. 2021;34: 18075–18086.
42.
Gill PE, Murray W, Wright MH. Practical optimization. SIAM. 2019.
43.
Bourtoule L, Chandrasekaran V, Choquette-Choo CA, Jia H, Travers A, Zhang B, Lie D, Papernot N, Machine unlearning, in,. IEEE Symposium on Security and Privacy (SP). IEEE. 2021;2021:141–59.
44.
45.
Welsch RE. Influence functions and regression diagnostics, in Modern data analysis. Elsevier. 1982;149–169.
46.
47.
Van Dyk DA, Meng X-L. The art of data augmentation. J Comput Graph Stat. 2001;10(1):1–50.
48.
49.
Allison B, Guthrie D, Guthrie L. Another look at the data sparsity problem. InText, Speech and Dialogue: 9th International Conference, TSD 2006, Brno, Czech Republic, September 11-15, 2006. Proceedings 9. Springer. 2006;327–34.
50.
Zhang Y, Yang Q. An overview of multi-task learning. Natl Sci Rev. 2018;5(1):30–43.CrossRef
51.
Laal M, Salamati P. Lifelong learning; why do we need it? Procedia Soc Behav Sci. 2012;31:399–403.CrossRef
52.
53.
Nguyen TT, Duong CT, Weidlich M, Yin H, Nguyen QVH. Retaining data from streams of social platforms with minimal regret, in Twenty-sixth International Joint Conference on Artificial Intelligence, no. CONF. 2017.
54.
55.
56.
57.
Ginart A, Guan M, Valiant G, Zou JY. Making AI forget you: data deletion in machine learning. Adv Neural Inf Process Sys. 2019;32.
58.
Brophy J, Lowd D. Machine unlearning for random forests, in International Conference on Machine Learning. PMLR. 2021;1092–1104.
59.
Thudi A, Deza G, Chandrasekaran V, Papernot N, Unrolling sgd: understanding factors influencing machine unlearning, in,. IEEE 7th European Symposium on Security and Privacy (EuroS&P). IEEE. 2022;2022:303–19.
60.
Neel S, Roth A, Sharifi-Malvajerdi S. Descent-to-delete: gradient-based methods for machine unlearning, in Algorithmic Learning Theory. PMLR. 2021;931–962.
61.
Graves L, Nagisetty V, Ganesh V. Amnesiac machine learning, in Proceedings of the AAAI Conference on Artificial Intelligence. 2021;35(13):11516–11524.
62.
Dwork C, Differential privacy: a survey of results, in International conference on theory and applications of models of computation. Springer. 2008;1–19.
63.
Cao Y, Yang J, Towards making systems forget with machine unlearning, in,. IEEE Symposium on Security and Privacy. IEEE. 2015;2015:463–80.
64.
Cauwenberghs G, Poggio T. Incremental and decremental support vector machine learning. Adv Neural Inf Process Sys. 2000;13.
65.
Chen Y, Xiong J, Xu W, Zuo J. A novel online incremental and decremental learning algorithm based on variable support vector machine. Clust Comput. 2019;22(3):7435–45.CrossRef
66.
67.
Schelter S, Grafberger S, Dunning T, Hedgecut: maintaining randomised trees for low-latency machine unlearning, in Proceedings of the 2021 International Conference on Management of Data. 2021;1545–1557.
68.
Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Mach Learn. 2006;63(1):3–42.CrossRef
69.
Golatkar A, Achille A, Soatto S. Forgetting outside the box: scrubbing deep networks of information accessible from input-output observations, in European Conference on Computer Vision. Springer. 2020; 383–398.
70.
Golatkar A, Achille A, Ravichandran A, Polito M, Soatto S. Mixed-privacy forgetting in deep networks, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021;792–801.
71.
72.
Koch K, Soll M. No matter how you slice it: machine unlearning with sisa comes at the expense of minority classes, in 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). IEEE. 2023;622–637.
73.
Mahmud MS, Huang JZ, Salloum S, Emara TZ. and K. Sadat- diynov, A survey of data partitioning and sampling methods to support big data analysis, Big Data Mining and Analytics. 2020;3(2):85–101.
74.
Picard RR, Berk KN. Data splitting. The American Statisti- cian. 1990;44(2):140–7.
75.
76.
Ul Hassan M, Rehmani MH, Rehan M, Chen J. Differential privacy in cognitive radio networks: a comprehensive survey. Cognitive Computation. 2022;1–36.
77.
Szo¨re´nyi B. Characterizing statistical query learning: simplified notions and proofs, in International Conference on Algorithmic Learning Theory. Springer. 2009;186–200.
78.
79.
Zhou Y, Huang K, Cheng C, Wang X, Hussain A, Liu X. Fastadabelief: improving convergence rate for belief-based adaptive optimizers by exploiting strong convexity. IEEE Transactions on Neural Networks and Learning Systems. 2022.
80.
Ralambondrainy H. A conceptual version of the k-means algorithm. Pattern Recogn Lett. 1995;16(11):1147–57.CrossRef
81.
Karasuyama M, Takeuchi I. Multiple incremental decremental learning of support vector machines. IEEE Trans Neural Networks. 2010;21(7):1048–59.CrossRef
82.
Joyce JM. Kullback-leibler divergence, in International encyclope- dia of statistical science. Springer. 2011;720–722.
83.
Clark LA, Pregibon D. Tree-based models, in Statistical models in S. Routledge. 2017;377–419.
84.
Myles AJ, Feudale RN, Liu Y, Woody NA, Brown SD. An introduction to decision tree modeling. Journal of Chemometrics: A Journal of the Chemometrics Society. 2004;18(6):275–85.CrossRef
85.
86.
Zhang Q, Zhong G, Dong J. A graph-based semi-supervised multi-label learning method based on label correlation consistency. Cogn Comput. 2021;13(6):1564–73.CrossRef
87.
Miikkulainen R, Liang J, Meyerson E, Rawal A, Fink D, Fran- con O, Raju B, Shahrzad H, Navruzyan A, Duffy N, et al. Evolving deep neural networks, in Artificial intelligence in the age of neural networks and brain computing. Elsevier. 2019;293–312.
88.
89.
Chhikara P, Tekchandani R, Kumar N, Chamola V, Guizani M. Dcnn-ga: a deep neural net architecture for navigation of uav in indoor environment. IEEE Internet Things J. 2020;8(6):4448–60.CrossRef
90.
Mahmud M, Kaiser MS, Hussain A, Vassanelli S. Applications of deep learning and reinforcement learning to biological data. IEEE transactions on neural networks and learning systems. 2018;29(6):2063–79.MathSciNetCrossRef
91.
Boyd SP, Vandenberghe L. Convex optimization. Cambridge university press. 2004.
92.
93.
Freese F, et al. Testing accuracy. Forest Sci. 1960;6(2):139–45.
94.
Hagenbach J, Koessler F. The Streisand effect: signaling and partial sophistication. J Econ Behav Organ. 2017;143:1–8.CrossRef
95.
Swiler LP, Paez TL, Mayes RL. Epistemic uncertainty quantification tutorial, in Proceedings of the 27th International Modal Analysis Conference. 2009.
96.
97.
98.
Shuvo MSR, Alhadidi D. Membership inference attacks: analysis and mitigation, in 2020 IEEE 19th International Conference on Trust. Security and Privacy in Computing and Communications (TrustCom). 2020;1410–1419.
99.
Liu X, Xie L, Wang Y, Zou J, Xiong J, Ying Z, Vasilakos AV. Privacy and security issues in deep learning: a survey. IEEE Access. 2020;9:4566–93.CrossRef
100.
Chundawat VS, Tarun AK, Mandal M, Kankanhalli M. Zeroshot machine unlearning. IEEE Transactions on Information Forensics and Security. 2023.
101.
102.
Fredrikson M. Jha S, Ristenpart T. Model inversion attacks that exploit confidence information and basic countermeasures, in Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, ser. CCS ’15. New York, NY, USA: Association for Computing Machinery. 2015;1322–1333. [Online]. Available: https://​doi.​org/​10.​1145/​2810103.​2813677.
103.
Xian Y, Lampert CH, Schiele B, Akata Z. Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans Pattern Anal Mach Intell. 2018;41(9):2251–65.CrossRef
104.
Golatkar A, Achille A, Soatto S. Eternal sunshine of the spotless net: Selective forgetting in deep networks, in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020;9304–9312.
105.
106.
107.
Wiedmann T, Minx J. A definition of ‘carbon footprint.’ Eco- logical economics research trends. 2008;1(2008):1–11.
108.
Henderson P, Hu J, Romoff J, Brunskill E, Jurafsky D, Pineau J. Towards the systematic reporting of the energy and carbon footprints of machine learning. J Mach Learn Res. 2020;21(1):10039–10081.
109.
L. F. W. Anthony, B. Kanding, and R. Selvan, Carbontracker: tracking and predicting the carbon footprint of training deep learning models. arXiv preprint. http://​arXiv:​2007.​03051. 2020.
110.
T. Alladi, B. Gera, A. Agrawal, V. Chamola, and F. R. Yu, Deepadv: a deep neural network framework for anomaly detection in vanets. IEEE Transactions on Vehicular Technology. 2021;70(11):12013–12023.
111.
Shokri R, Stronati M, Song C, Shmatikov V, Membership inference attacks against machine learning models, in,. IEEE symposium on security and privacy (SP). IEEE. 2017;2017:3–18.
112.
Zhang C, Xie Y, Bai H, Yu B, Li W, Gao Y. A survey on federated learning. Knowl-Based Syst. 2021;216: 106775.CrossRef
113.
Li L, Fan Y, Tse M, Lin K-Y. A review of applications in federated learning. Comput Ind Eng. 2020;149: 106854.CrossRef
114.
Li T, Sahu AK, Talwalkar A, Smith V. Federated learning: challenges, methods, and future directions. IEEE Signal Process Mag. 2020;37(3):50–60.CrossRef
115.
Aspin DN, Chapman JD. Lifelong learning: concepts and conceptions. Int J Lifelong Educ. 2000;19(1):2–19.CrossRef
116.
Thrun S. Lifelong learning algorithms Learning to learn. 1998;8:181–209.
117.
118.
Yapo A, Weiss J. Ethical implications of bias in machine learning, 2018.
119.
Roscher R, Bohn B, Duarte MF, Garcke J. Explainable machine learning for scientific insights and discoveries. Ieee Access. 2020;8:42200–42216.
120.
Belle V, Papantonis I. Principles and practice of explainable machine learning. Frontiers in big Data. 2021;39.
121.
122.
Ribeiro MT, Singh S, Guestrin C. Why should I trust you?: explaining the predictions of any classifier, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August. 2016;1135–1144.
123.
124.
Schwartz R, Dodge J, Smith NA, Etzioni O. Green AI. Commun ACM. 2020;63(12):54–63.CrossRef
125.
126.
127.
Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, et al. Language models are few-shot learners. Adv Neural Inf Process Syst. 2020;33:1877–901.
128.
Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ, et al. Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res. 2020;21(140):1–67.MathSciNet
129.
Fedus W, Zoph B, Shazeer N. Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. 2021.
130.
131.
Apte C, The role of machine learning in business optimization, in Proceedings of the 27th International Conference on Machine Learning (ICML-10). Citeseer. 2010;1–2.
132.
Singh S, Sulthana R, Shewale T, Chamola V, Benslimane A, Sikdar B. Machine-learning-assisted security and privacy provisioning for edge computing: a survey. IEEE Internet Things J. 2021;9(1):236–60.CrossRef
133.
Miao Y, Chen C, Pan L, Han Q-L, Zhang J, Xiang Y. Machine learning–based cyber attacks targeting on controlled information: a survey. ACM Computing Surveys (CSUR). 2021;54(7):1–36.CrossRef
134.
Wazid M, Das AK, Chamola V, Park Y. Uniting cyber security and machine learning: advantages, challenges and future research. ICT Express. 2022;8(3):313–21.CrossRef
135.
Chamola V, Goyal A, Sharma P, Hassija V, Binh HTT, Saxena V. Artificial intelligence-assisted blockchain-based framework for smart and secure emr management. Neural Computing and Appli- cations. 2022;1–11.
136.
Isinkaye FO, Folajimi YO, Ojokoh BA. Recommendation systems: principles, methods and evaluation. Egypt Inform J. 2015;16(3):261–73.
137.
Pavithra D. Jayanthi A. A study on machine learning algorithm in medical diagnosis. Int J Adv Res Comput Sci. 2018;9(4).
138.
Rohmetra H, Raghunath N, Narang P, Chamola V, Guizani M, Lakkaniga NR. AI-enabled remote monitoring of vital signs for covid-19: methods, prospects and challenges. Computing. 2021;1–27.
139.
Bansal G, Chamola V, Narang P, Kumar S, Raman S. Deep3dscan: deep residual network and morphological descriptor based framework forlung cancer classification and 3d segmentation. IET Image Proc. 2020;14(7):1240–7.CrossRef
140.
Delgado-Rodriguez M, Llorca Bias J. Journal of Epidemiology & Community Health. 2004;58(8):635–641.
141.
Danks D, London AJ. Algorithmic bias in autonomous systems. Ijcai. 2017;17(2017):4691–7.
142.
Malerba D, Esposito F, Lanza A, Lisi FA. Machine learning for information extraction from topographic maps. Geographic data mining and knowledge discovery. 2001;291–314.
143.
Hutchins WJ, Machine translation: past, present, future. Ellis Horwood Chichester. 1986.
144.
Grieco LA, Rizzo A, Colucci S, Sicari S, Piro G, Di Paola D, Boggia G. IoT-aided robotics applications: technological implications, target domains and open issues. Comput Commun. 2014;54:32–47.CrossRef
145.
Roy Chowdhury A, Iot and robotics: a synergy. PeerJ Preprints. 2017;5:e2760v1.
146.
Zhao W, Chellappa R, Phillips PJ, Rosenfeld A. Face recognition: a literature survey. ACM computing surveys (CSUR). 2003;35(4):399–458.CrossRef
147.
Hernandez G, Arias O, Buentello D, Jin Y, Smart nest thermostat: a smart spy in your home. Black Hat USA. no. 2015, 2014.
148.
149.
Gogate M, Dashtipour K, Adeel A, Hussain A. Cochleanet: a robust language-independent audio-visual model for real-time speech enhancement. Information Fusion. 2020;63:273–85.CrossRef
150.
151.
Adeel A, Gogate M, Hussain A. Contextual deep learning- based audio-visual switching for speech enhancement in real-world environments. Information Fusion. 2020;59:163–70.CrossRef
152.
Alladi T, Kohli V, Chamola V, Yu FR, Securing the internet of vehicles: a deep learning based classification framework. IEEE Networking Letters. 2021.
153.
Wang W, Zheng VW, Yu H, Miao C. A survey of zero-shot learning: settings, methods, and applications. ACM Transactions on Intelligent Systems and Technology (TIST). 2019;10(2):1–37.
154.
Wang Y, Yao Q, Kwok JT, Ni LM. Generalizing from a few examples: a survey on few-shot learning. ACM computing surveys (csur). 2020;53(3):1–34.CrossRef
155.
Rahman S, Khan S, Porikli F. A unified approach for conventional zero-shot, generalized zero-shot, and few-shot learning. IEEE Trans Image Process. 2018;27(11):5652–67.MathSciNetCrossRef
Metadata
Title
Machine Un-learning: An Overview of Techniques, Applications, and Future Directions
Authors
Siva Sai
Uday Mittal
Vinay Chamola
Kaizhu Huang
Indro Spinelli
Simone Scardapane
Zhiyuan Tan
Amir Hussain
Publication date
04-11-2023
Publisher
Springer US
Published in
Cognitive Computation / Issue 2/2024
Print ISSN: 1866-9956
Electronic ISSN: 1866-9964
DOI
https://doi.org/10.1007/s12559-023-10219-3

Other articles of this Issue 2/2024

Cognitive Computation 2/2024 Go to the issue

OriginalPaper

A Cognitively Inspired Multi-granularity Model Incorporating Label Information for Complex Long Text Classification

OriginalPaper

AGD-Net: Attention-Guided Dense Inception U-Net for Single-Image Dehazing

OriginalPaper

A Novel Regularized Extreme Learning Machine Based on -Norm and -Norm: a Sparsity Solution Alternative to Lasso and Elastic Net

OriginalPaper

A Novel Cognitively Inspired Deep Learning Approach to Detect Drivable Areas for Self-driving Cars

OriginalPaper

A Novel Feature Fusion Approach for Classification of Motor Imagery EEG Based on Hierarchical Extreme Learning Machine

OriginalPaper

A Novel Heuristic Exploration Method Based on Action Effectiveness Constraints to Relieve Loop Enhancement Effect in Reinforcement Learning with Sparse Rewards

Premium Partner

    Image Credits