Federated Incremental Learning algorithm based on Topological Data Analysis
Federated learning is a distributed learning approach aimed at preserving user’s data privacy, while incremental learning is an adaptive machine learning method that enables continuous learning of new data. The combination of these two approaches into Federated Incremental Learning (FIL) algorithms...
Uloženo v:
| Vydáno v: | Pattern recognition Ročník 158; s. 111048 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.02.2025
|
| Témata: | |
| ISSN: | 0031-3203 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Federated learning is a distributed learning approach aimed at preserving user’s data privacy, while incremental learning is an adaptive machine learning method that enables continuous learning of new data. The combination of these two approaches into Federated Incremental Learning (FIL) algorithms brings together their respective advantages. However, the existing federated incremental learning still faces two main challenges: (1) catastrophic forgetting of previous knowledge by local models when adapting to incremental tasks, and (2) limited capability of the server to capture critical features during federated aggregation. To address these challenges, this paper proposes a federated incremental learning algorithm based on Topological Data Analysis (TDA). Firstly, the algorithm extracts topological features from the input information and designs a Topological Stability Loss (TSL) to mitigate catastrophic forgetting of previous knowledge by local models. Secondly, a feature attention mechanism is utilized to select appropriate attention weights for each local model, enhancing the recognition performance of the global model. The experimental results on publicly available datasets, namely CIFAR10, CIFAR100, and ImageNet, demonstrate that the proposed approach in this paper achieves global accuracies of 67.23%, 65.75%, and 62.41% respectively for the federated incremental learning model. These accuracies surpass the existing Icarl incremental algorithm by improvements of 3.21%, 2.87%, and 1.34% respectively. Therefore, the algorithm presented in this paper achieves better performance, indicating its superiority over existing methods.
•Proposes a topological stability loss function based on Topological Data Analysis (TDA).•Presenting a federated incremental learning framework that incorporates the detection of new class tasks based on changes in the local model’s topological structure. |
|---|---|
| AbstractList | Federated learning is a distributed learning approach aimed at preserving user’s data privacy, while incremental learning is an adaptive machine learning method that enables continuous learning of new data. The combination of these two approaches into Federated Incremental Learning (FIL) algorithms brings together their respective advantages. However, the existing federated incremental learning still faces two main challenges: (1) catastrophic forgetting of previous knowledge by local models when adapting to incremental tasks, and (2) limited capability of the server to capture critical features during federated aggregation. To address these challenges, this paper proposes a federated incremental learning algorithm based on Topological Data Analysis (TDA). Firstly, the algorithm extracts topological features from the input information and designs a Topological Stability Loss (TSL) to mitigate catastrophic forgetting of previous knowledge by local models. Secondly, a feature attention mechanism is utilized to select appropriate attention weights for each local model, enhancing the recognition performance of the global model. The experimental results on publicly available datasets, namely CIFAR10, CIFAR100, and ImageNet, demonstrate that the proposed approach in this paper achieves global accuracies of 67.23%, 65.75%, and 62.41% respectively for the federated incremental learning model. These accuracies surpass the existing Icarl incremental algorithm by improvements of 3.21%, 2.87%, and 1.34% respectively. Therefore, the algorithm presented in this paper achieves better performance, indicating its superiority over existing methods.
•Proposes a topological stability loss function based on Topological Data Analysis (TDA).•Presenting a federated incremental learning framework that incorporates the detection of new class tasks based on changes in the local model’s topological structure. |
| ArticleNumber | 111048 |
| Author | Jiang, Shanshan Hu, Kai Li, YaoGen Gong, Sheng Li, Lingxiao Luo, Yuantu |
| Author_xml | – sequence: 1 givenname: Kai orcidid: 0000-0001-7181-9935 surname: Hu fullname: Hu, Kai email: 001600@nuist.edu.cn organization: School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China – sequence: 2 givenname: Sheng orcidid: 0000-0001-9726-2338 surname: Gong fullname: Gong, Sheng email: 20211249032@nuist.edu.cn organization: School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China – sequence: 3 givenname: Lingxiao orcidid: 0009-0005-2290-3969 surname: Li fullname: Li, Lingxiao email: 202312490034@nuist.edu.cn organization: School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China – sequence: 4 givenname: Yuantu orcidid: 0009-0003-0448-2502 surname: Luo fullname: Luo, Yuantu email: 220225006@seu.edu.cn organization: Cyber Science & Engineering, Nanjing University of Southeast, Nanjing 211189, China – sequence: 5 givenname: YaoGen orcidid: 0000-0001-7745-1713 surname: Li fullname: Li, YaoGen email: 230238080@seu.edu.cn organization: School of Automation, Nanjing University of Information Science and Technology, Nanjing 210044, China – sequence: 6 givenname: Shanshan orcidid: 0000-0001-7734-5136 surname: Jiang fullname: Jiang, Shanshan email: jss@nuist.edu.cn organization: School of management science and engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China |
| BookMark | eNp9kL1OwzAUhT0UibbwBgx5gQRf22mTBakqFCoqsZTZ8s91cJXalR0h9e0JCjPTWc75dPQtyCzEgIQ8AK2AwurxVF3UYGJXMcpEBQBUNDMyp5RDyRnlt2SR84lSWINgc_K-Q4tJDWiLfTAJzxgG1RcHVCn40BWq72Lyw9e50CqPpRiKY7zEPnbejL1nNahiE1R_zT7fkRun-oz3f7kkn7uX4_atPHy87rebQ2lYXQ-l0E5z0Zq2dlq4VdtoXGu21rUB52qmLHAFogZw1DqjWorWcWibFXONrXXDl0RMXJNizgmdvCR_VukqgcpfCfIkJwnyV4KcJIyzp2mG47dvj0lm4zEYtD6hGaSN_n_AD5bObDs |
| Cites_doi | 10.1016/j.eswa.2023.121463 10.1016/j.engappai.2021.104468 10.1145/3298981 10.1016/S0079-7421(08)60536-8 10.3390/math10061000 10.1016/S0031-3203(01)00238-2 10.1016/j.tics.2020.09.004 10.1109/ICCV48922.2021.00088 10.3390/electronics11223668 10.1109/ICCV.2017.368 10.3390/rs14010206 10.18653/v1/2020.coling-main.392 10.1117/1.JRS.16.016513 10.1002/int.22727 10.1126/science.7134969 10.1109/CVPR.2019.00092 10.1109/CVPR.2017.587 10.1109/TPAMI.2020.3013679 10.3390/app121910025 10.1609/aaai.v35i9.16991 10.1155/2021/8261663 10.1167/19.7.12 10.1109/CVPR52688.2022.00992 10.1523/JNEUROSCI.2789-16.2016 10.1109/TPWRD.2021.3124528 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Ltd |
| Copyright_xml | – notice: 2024 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.patcog.2024.111048 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| ExternalDocumentID | 10_1016_j_patcog_2024_111048 S0031320324007994 |
| GroupedDBID | --K --M -D8 -DT -~X .DC .~1 0R~ 123 1B1 1RT 1~. 1~5 29O 4.4 457 4G. 53G 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXKI AAXUO AAYFN ABBOA ABDPE ABEFU ABFNM ABFRF ABHFT ABJNI ABMAC ABTAH ABXDB ACBEA ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADMXK ADTZH AEBSH AECPX AEFWE AEKER AENEX AFJKZ AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F0J F5P FD6 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM KZ1 LG9 LMP LY1 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SST SSV SSZ T5K TN5 UNMZH VOH WUQ XJE XPP ZMT ZY4 ~G- 9DU AATTM AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP ANKPU APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c255t-4bfb349c95fb4f698be7b27b5c1ff52ad13a14511f0dfca90edf319862f8d5b83 |
| ISICitedReferencesCount | 2 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001331831600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0031-3203 |
| IngestDate | Sat Nov 29 03:52:41 EST 2025 Sat Nov 16 15:59:03 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Incremental learning Federated learning Topological Data Analysis |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c255t-4bfb349c95fb4f698be7b27b5c1ff52ad13a14511f0dfca90edf319862f8d5b83 |
| ORCID | 0000-0001-7181-9935 0009-0003-0448-2502 0000-0001-7734-5136 0000-0001-7745-1713 0009-0005-2290-3969 0000-0001-9726-2338 |
| ParticipantIDs | crossref_primary_10_1016_j_patcog_2024_111048 elsevier_sciencedirect_doi_10_1016_j_patcog_2024_111048 |
| PublicationCentury | 2000 |
| PublicationDate | February 2025 2025-02-00 |
| PublicationDateYYYYMMDD | 2025-02-01 |
| PublicationDate_xml | – month: 02 year: 2025 text: February 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Pattern recognition |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | S. Hou, X. Pan, C.C. Loy, Z. Wang, D. Lin, Learning a unified classifier incrementally via rebalancing, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 831–839. Qiang, Liang, Wan, Zhang (b22) 2024 Wei, Zhou, Zhang, Zhuo, Chen (b30) 2019; 19 Balaban, Luria (b32) 2017; 37 Wang, Zhou, Zhang, Zhan, Ye (b23) 2024; 36 D. Zhang, X. Chen, S. Xu, B. Xu, Knowledge aware emotion recognition in textual conversations via multi-task incremental transformer, in: Proceedings of the 28th International Conference on Computational Linguistics, 2020, pp. 4429–4440. Wang, Xia, Lu, Pan, Liu (b43) 2021; 37 Hu, Li, Zhang, Wu, Gong, Jiang, Weng (b3) 2024; 237 Tao, Chang, Hong, Wei, Gong (b12) 2020 Che, Galaz-García, Guijarro, Solis, Valiunas (b40) 2022 Meng, Zhang, Yang, Zhan, Zhao, WAng (b24) 2024 Babakniya, Fabian, He, Soltanolkotabi, Avestimehr (b11) 2024; 36 McCloskey, Cohen (b29) 1989; Vol. 24 Blanco-Justicia, Domingo-Ferrer, Martínez, Sánchez, Flanagan, Tan (b13) 2021; 106 Douillard, Cord, Ollion, Robert, Valle (b17) 2020 Hu, Li, Xia, Wu, Lu, Zhang, Weng (b2) 2021; 2021 Li, Sahu, Zaheer, Sanjabi, Talwalkar, Smith (b5) 2020; 2 Kaji, Sudo, Ahara (b34) 2020 McMahan, Moore, Ramage, Hampson, y Arcas (b4) 2017 J.-Y. Kim, D.-W. Choi, Split-and-bridge: Adaptable class incremental learning within a single neural network, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 8137–8145. Gao, Weng, Xia, Lin (b42) 2022; 16 Hadsell, Rao, Rusu, Pascanu (b1) 2020; 24 Garin, Tauzin (b33) 2019 K. Shmelkov, C. Schmid, K. Alahari, Incremental learning of object detectors without catastrophic forgetting, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 3400–3409. Hu, Li, Xia, Lin (b41) 2022; 14 Wang, Liang, Koe, Wu, Zhang, Li, Yang (b8) 2022; 37 S.-A. Rebuffi, A. Kolesnikov, G. Sperl, C.H. Lampert, icarl: Incremental classifier and representation learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2001–2010. Pun, Xia, Lee (b25) 2018 Saadat-Yazdi, Andreeva, Sarkar (b39) 2021 Bubenik (b38) 2015; 16 Clough, Byrne, Oksuz, Zimmer, Schnabel, King (b26) 2020; 44 Park, Kumatani, Dimitriadis (b9) 2021 Hu, Lu, Li, Gong, Wu, Zhou, Jiang, Yang (b6) 2022; 12 H. Ahn, J. Kwak, S. Lim, H. Bang, H. Kim, T. Moon, Ss-il: Separated softmax for incremental learning, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 844–853. Ziou, Allili (b36) 2002; 35 J. Dong, L. Wang, Z. Fang, G. Sun, S. Xu, X. Wang, Q. Zhu, Federated class-incremental learning, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10164–10173. Shoham, Avidor, Keren, Israel, Benditkis, Mor-Yosef, Zeitak (b21) 2019 Lei, Wang, Zhong, Wang, Ng (b10) 2022; 11 Hu, Wu, Li, Lu, Weng, Xia (b14) 2022; 10 Yang, Liu, Chen, Tong (b15) 2019; 10 Goodfellow, Mirza, Xiao, Courville, Bengio (b28) 2013 Chen (b31) 1982; 218 Karaca, Ege (b37) 2012; 1 Allili, Mischaikow, Tannenbaum (b35) 2001; Vol. 2 Lei (10.1016/j.patcog.2024.111048_b10) 2022; 11 Shoham (10.1016/j.patcog.2024.111048_b21) 2019 Qiang (10.1016/j.patcog.2024.111048_b22) 2024 Bubenik (10.1016/j.patcog.2024.111048_b38) 2015; 16 Che (10.1016/j.patcog.2024.111048_b40) 2022 Meng (10.1016/j.patcog.2024.111048_b24) 2024 Balaban (10.1016/j.patcog.2024.111048_b32) 2017; 37 Pun (10.1016/j.patcog.2024.111048_b25) 2018 Gao (10.1016/j.patcog.2024.111048_b42) 2022; 16 Hu (10.1016/j.patcog.2024.111048_b6) 2022; 12 Allili (10.1016/j.patcog.2024.111048_b35) 2001; Vol. 2 Hu (10.1016/j.patcog.2024.111048_b2) 2021; 2021 10.1016/j.patcog.2024.111048_b27 Park (10.1016/j.patcog.2024.111048_b9) 2021 Hu (10.1016/j.patcog.2024.111048_b14) 2022; 10 Hu (10.1016/j.patcog.2024.111048_b3) 2024; 237 Saadat-Yazdi (10.1016/j.patcog.2024.111048_b39) 2021 Garin (10.1016/j.patcog.2024.111048_b33) 2019 Karaca (10.1016/j.patcog.2024.111048_b37) 2012; 1 Li (10.1016/j.patcog.2024.111048_b5) 2020; 2 10.1016/j.patcog.2024.111048_b7 Clough (10.1016/j.patcog.2024.111048_b26) 2020; 44 Goodfellow (10.1016/j.patcog.2024.111048_b28) 2013 McMahan (10.1016/j.patcog.2024.111048_b4) 2017 Blanco-Justicia (10.1016/j.patcog.2024.111048_b13) 2021; 106 Wei (10.1016/j.patcog.2024.111048_b30) 2019; 19 10.1016/j.patcog.2024.111048_b18 10.1016/j.patcog.2024.111048_b19 Chen (10.1016/j.patcog.2024.111048_b31) 1982; 218 Kaji (10.1016/j.patcog.2024.111048_b34) 2020 Tao (10.1016/j.patcog.2024.111048_b12) 2020 Hu (10.1016/j.patcog.2024.111048_b41) 2022; 14 10.1016/j.patcog.2024.111048_b16 10.1016/j.patcog.2024.111048_b20 Ziou (10.1016/j.patcog.2024.111048_b36) 2002; 35 Yang (10.1016/j.patcog.2024.111048_b15) 2019; 10 10.1016/j.patcog.2024.111048_b44 Wang (10.1016/j.patcog.2024.111048_b23) 2024; 36 McCloskey (10.1016/j.patcog.2024.111048_b29) 1989; Vol. 24 Wang (10.1016/j.patcog.2024.111048_b8) 2022; 37 Hadsell (10.1016/j.patcog.2024.111048_b1) 2020; 24 Douillard (10.1016/j.patcog.2024.111048_b17) 2020 Wang (10.1016/j.patcog.2024.111048_b43) 2021; 37 Babakniya (10.1016/j.patcog.2024.111048_b11) 2024; 36 |
| References_xml | – volume: 10 start-page: 1000 year: 2022 ident: b14 article-title: Fedgcn: Federated learning-based graph convolutional networks for non-euclidean spatial data publication-title: Mathematics – year: 2020 ident: b34 article-title: Cubical ripser: Software for computing persistent homology of image and volume data – volume: 12 start-page: 10025 year: 2022 ident: b6 article-title: A federated incremental learning algorithm based on dual attention mechanism publication-title: Appl. Sci. – reference: J.-Y. Kim, D.-W. Choi, Split-and-bridge: Adaptable class incremental learning within a single neural network, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35, 2021, pp. 8137–8145. – reference: D. Zhang, X. Chen, S. Xu, B. Xu, Knowledge aware emotion recognition in textual conversations via multi-task incremental transformer, in: Proceedings of the 28th International Conference on Computational Linguistics, 2020, pp. 4429–4440. – reference: K. Shmelkov, C. Schmid, K. Alahari, Incremental learning of object detectors without catastrophic forgetting, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 3400–3409. – volume: 2 start-page: 429 year: 2020 end-page: 450 ident: b5 article-title: Federated optimization in heterogeneous networks publication-title: Proc. Mach. Learn. Syst. – volume: 10 start-page: 1 year: 2019 end-page: 19 ident: b15 article-title: Federated machine learning: Concept and applications publication-title: ACM Trans. Intell. Syst. Technol. – volume: 36 year: 2024 ident: b23 article-title: Few-shot class-incremental learning via training-free prototype calibration publication-title: Adv. Neural Inf. Process. Syst. – volume: 14 start-page: 206 year: 2022 ident: b41 article-title: Multi-scale feature aggregation network for water area segmentation publication-title: Remote Sens. – volume: 16 start-page: 016513 year: 2022 ident: b42 article-title: MLNet: Multichannel feature fusion lozenge network for land segmentation publication-title: J. Appl. Remote Sens. – start-page: 119 year: 2021 end-page: 128 ident: b39 article-title: Topological detection of Alzheimer’s disease using Betti curves publication-title: Interpretability of Machine Intelligence in Medical Image Computing, and Topological Data Analysis and Its Applications for Medical Data: 4th International Workshop, IMIMIC 2021, and 1st International Workshop, TDA4MedicalData 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings 4 – reference: S. Hou, X. Pan, C.C. Loy, Z. Wang, D. Lin, Learning a unified classifier incrementally via rebalancing, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 831–839. – volume: 106 year: 2021 ident: b13 article-title: Achieving security and privacy in federated learning systems: Survey, research challenges and future directions publication-title: Eng. Appl. Artif. Intell. – year: 2024 ident: b22 article-title: Dynamic feature learning and matching for class-incremental learning – volume: 19 start-page: 12 year: 2019 ident: b30 article-title: Visual working memory representation as a topological defined perceptual object publication-title: J. Vis. – volume: 35 start-page: 2833 year: 2002 end-page: 2839 ident: b36 article-title: Generating cubical complexes from image data and computation of the Euler number publication-title: Pattern Recognit. – year: 2018 ident: b25 article-title: Persistent-homology-based machine learning and its applications–A survey – start-page: 86 year: 2020 end-page: 102 ident: b17 article-title: Podnet: Pooled outputs distillation for small-tasks incremental learning publication-title: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XX 16 – volume: 1 start-page: 178 year: 2012 end-page: 187 ident: b37 article-title: Cubical homology in digital images publication-title: Int. J. Inf. Comput. Sci. – start-page: 254 year: 2020 end-page: 270 ident: b12 article-title: Topology-preserving class-incremental learning publication-title: Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIX 16 – volume: 16 start-page: 77 year: 2015 end-page: 102 ident: b38 article-title: Statistical topological data analysis using persistence landscapes publication-title: J. Mach. Learn. Res. – year: 2021 ident: b9 article-title: Tackling dynamics in federated incremental learning with variational embedding rehearsal – reference: S.-A. Rebuffi, A. Kolesnikov, G. Sperl, C.H. Lampert, icarl: Incremental classifier and representation learning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2001–2010. – volume: 237 year: 2024 ident: b3 article-title: FedMMD: A federated weighting algorithm considering non-IID and local model deviation publication-title: Expert Syst. Appl. – volume: 37 start-page: 3155 year: 2021 end-page: 3163 ident: b43 article-title: Parameter identification in power transmission systems based on graph convolution network publication-title: IEEE Trans. Power Deliv. – year: 2019 ident: b21 article-title: Overcoming forgetting in federated learning on non-iid data – start-page: 1273 year: 2017 end-page: 1282 ident: b4 article-title: Communication-efficient learning of deep networks from decentralized data publication-title: Artificial Intelligence and Statistics – volume: 24 start-page: 1028 year: 2020 end-page: 1040 ident: b1 article-title: Embracing change: Continual learning in deep neural networks publication-title: Trends Cogn. Sci. – volume: 218 start-page: 699 year: 1982 end-page: 700 ident: b31 article-title: Topological structure in visual perception publication-title: Science – reference: J. Dong, L. Wang, Z. Fang, G. Sun, S. Xu, X. Wang, Q. Zhu, Federated class-incremental learning, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10164–10173. – start-page: 1551 year: 2019 end-page: 1556 ident: b33 article-title: A topological” reading” lesson: Classification of MNIST using TDA publication-title: 2019 18th IEEE International Conference on Machine Learning and Applications – volume: 37 start-page: 4471 year: 2022 end-page: 4487 ident: b8 article-title: Secure and efficient parameters aggregation protocol for federated incremental learning and its applications publication-title: Int. J. Intell. Syst. – year: 2013 ident: b28 article-title: An empirical investigation of catastrophic forgetting in gradient-based neural networks – volume: 37 start-page: 1225 year: 2017 end-page: 1239 ident: b32 article-title: Neural and behavioral evidence for an online resetting process in visual working memory publication-title: J. Neurosci. – volume: 36 year: 2024 ident: b11 article-title: A data-free approach to mitigate catastrophic forgetting in federated class incremental learning for vision tasks publication-title: Adv. Neural Inf. Process. Syst. – volume: 44 start-page: 8766 year: 2020 end-page: 8778 ident: b26 article-title: A topological loss function for deep-learning based image segmentation using persistent homology publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: Vol. 24 start-page: 109 year: 1989 end-page: 165 ident: b29 article-title: Catastrophic interference in connectionist networks: The sequential learning problem publication-title: Psychology of Learning and Motivation – year: 2024 ident: b24 article-title: DiffClass: Diffusion-based class incremental learning – volume: 2021 start-page: 1 year: 2021 end-page: 20 ident: b2 article-title: Federated learning: a distributed shared machine learning method publication-title: Complexity – volume: Vol. 2 start-page: 173 year: 2001 end-page: 176 ident: b35 article-title: Cubical homology and the topological classification of 2D and 3D imagery publication-title: Proceedings 2001 International Conference on Image Processing (Cat. No. 01CH37205) – volume: 11 start-page: 3668 year: 2022 ident: b10 article-title: A federated learning framework based on incremental weighting and diversity selection for internet of vehicles publication-title: Electronics – year: 2022 ident: b40 article-title: Basic metric geometry of the bottleneck distance – reference: H. Ahn, J. Kwak, S. Lim, H. Bang, H. Kim, T. Moon, Ss-il: Separated softmax for incremental learning, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 844–853. – volume: 36 year: 2024 ident: 10.1016/j.patcog.2024.111048_b11 article-title: A data-free approach to mitigate catastrophic forgetting in federated class incremental learning for vision tasks publication-title: Adv. Neural Inf. Process. Syst. – volume: Vol. 2 start-page: 173 year: 2001 ident: 10.1016/j.patcog.2024.111048_b35 article-title: Cubical homology and the topological classification of 2D and 3D imagery – year: 2013 ident: 10.1016/j.patcog.2024.111048_b28 – volume: 237 year: 2024 ident: 10.1016/j.patcog.2024.111048_b3 article-title: FedMMD: A federated weighting algorithm considering non-IID and local model deviation publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.121463 – volume: 106 year: 2021 ident: 10.1016/j.patcog.2024.111048_b13 article-title: Achieving security and privacy in federated learning systems: Survey, research challenges and future directions publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2021.104468 – volume: 10 start-page: 1 issue: 2 year: 2019 ident: 10.1016/j.patcog.2024.111048_b15 article-title: Federated machine learning: Concept and applications publication-title: ACM Trans. Intell. Syst. Technol. doi: 10.1145/3298981 – volume: Vol. 24 start-page: 109 year: 1989 ident: 10.1016/j.patcog.2024.111048_b29 article-title: Catastrophic interference in connectionist networks: The sequential learning problem doi: 10.1016/S0079-7421(08)60536-8 – start-page: 86 year: 2020 ident: 10.1016/j.patcog.2024.111048_b17 article-title: Podnet: Pooled outputs distillation for small-tasks incremental learning – year: 2024 ident: 10.1016/j.patcog.2024.111048_b22 – start-page: 1551 year: 2019 ident: 10.1016/j.patcog.2024.111048_b33 article-title: A topological” reading” lesson: Classification of MNIST using TDA – volume: 10 start-page: 1000 issue: 6 year: 2022 ident: 10.1016/j.patcog.2024.111048_b14 article-title: Fedgcn: Federated learning-based graph convolutional networks for non-euclidean spatial data publication-title: Mathematics doi: 10.3390/math10061000 – volume: 35 start-page: 2833 issue: 12 year: 2002 ident: 10.1016/j.patcog.2024.111048_b36 article-title: Generating cubical complexes from image data and computation of the Euler number publication-title: Pattern Recognit. doi: 10.1016/S0031-3203(01)00238-2 – volume: 24 start-page: 1028 issue: 12 year: 2020 ident: 10.1016/j.patcog.2024.111048_b1 article-title: Embracing change: Continual learning in deep neural networks publication-title: Trends Cogn. Sci. doi: 10.1016/j.tics.2020.09.004 – volume: 16 start-page: 77 issue: 1 year: 2015 ident: 10.1016/j.patcog.2024.111048_b38 article-title: Statistical topological data analysis using persistence landscapes publication-title: J. Mach. Learn. Res. – ident: 10.1016/j.patcog.2024.111048_b18 doi: 10.1109/ICCV48922.2021.00088 – year: 2024 ident: 10.1016/j.patcog.2024.111048_b24 – volume: 11 start-page: 3668 issue: 22 year: 2022 ident: 10.1016/j.patcog.2024.111048_b10 article-title: A federated learning framework based on incremental weighting and diversity selection for internet of vehicles publication-title: Electronics doi: 10.3390/electronics11223668 – ident: 10.1016/j.patcog.2024.111048_b20 doi: 10.1109/ICCV.2017.368 – year: 2021 ident: 10.1016/j.patcog.2024.111048_b9 – volume: 14 start-page: 206 issue: 1 year: 2022 ident: 10.1016/j.patcog.2024.111048_b41 article-title: Multi-scale feature aggregation network for water area segmentation publication-title: Remote Sens. doi: 10.3390/rs14010206 – ident: 10.1016/j.patcog.2024.111048_b16 doi: 10.18653/v1/2020.coling-main.392 – volume: 36 year: 2024 ident: 10.1016/j.patcog.2024.111048_b23 article-title: Few-shot class-incremental learning via training-free prototype calibration publication-title: Adv. Neural Inf. Process. Syst. – volume: 16 start-page: 016513 issue: 1 year: 2022 ident: 10.1016/j.patcog.2024.111048_b42 article-title: MLNet: Multichannel feature fusion lozenge network for land segmentation publication-title: J. Appl. Remote Sens. doi: 10.1117/1.JRS.16.016513 – volume: 37 start-page: 4471 issue: 8 year: 2022 ident: 10.1016/j.patcog.2024.111048_b8 article-title: Secure and efficient parameters aggregation protocol for federated incremental learning and its applications publication-title: Int. J. Intell. Syst. doi: 10.1002/int.22727 – year: 2022 ident: 10.1016/j.patcog.2024.111048_b40 – year: 2018 ident: 10.1016/j.patcog.2024.111048_b25 – volume: 218 start-page: 699 issue: 4573 year: 1982 ident: 10.1016/j.patcog.2024.111048_b31 article-title: Topological structure in visual perception publication-title: Science doi: 10.1126/science.7134969 – ident: 10.1016/j.patcog.2024.111048_b27 doi: 10.1109/CVPR.2019.00092 – volume: 2 start-page: 429 year: 2020 ident: 10.1016/j.patcog.2024.111048_b5 article-title: Federated optimization in heterogeneous networks publication-title: Proc. Mach. Learn. Syst. – ident: 10.1016/j.patcog.2024.111048_b44 doi: 10.1109/CVPR.2017.587 – volume: 44 start-page: 8766 issue: 12 year: 2020 ident: 10.1016/j.patcog.2024.111048_b26 article-title: A topological loss function for deep-learning based image segmentation using persistent homology publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2020.3013679 – start-page: 1273 year: 2017 ident: 10.1016/j.patcog.2024.111048_b4 article-title: Communication-efficient learning of deep networks from decentralized data – volume: 12 start-page: 10025 issue: 19 year: 2022 ident: 10.1016/j.patcog.2024.111048_b6 article-title: A federated incremental learning algorithm based on dual attention mechanism publication-title: Appl. Sci. doi: 10.3390/app121910025 – year: 2020 ident: 10.1016/j.patcog.2024.111048_b34 – volume: 1 start-page: 178 year: 2012 ident: 10.1016/j.patcog.2024.111048_b37 article-title: Cubical homology in digital images publication-title: Int. J. Inf. Comput. Sci. – ident: 10.1016/j.patcog.2024.111048_b19 doi: 10.1609/aaai.v35i9.16991 – volume: 2021 start-page: 1 year: 2021 ident: 10.1016/j.patcog.2024.111048_b2 article-title: Federated learning: a distributed shared machine learning method publication-title: Complexity doi: 10.1155/2021/8261663 – year: 2019 ident: 10.1016/j.patcog.2024.111048_b21 – volume: 19 start-page: 12 issue: 7 year: 2019 ident: 10.1016/j.patcog.2024.111048_b30 article-title: Visual working memory representation as a topological defined perceptual object publication-title: J. Vis. doi: 10.1167/19.7.12 – ident: 10.1016/j.patcog.2024.111048_b7 doi: 10.1109/CVPR52688.2022.00992 – start-page: 119 year: 2021 ident: 10.1016/j.patcog.2024.111048_b39 article-title: Topological detection of Alzheimer’s disease using Betti curves – volume: 37 start-page: 1225 issue: 5 year: 2017 ident: 10.1016/j.patcog.2024.111048_b32 article-title: Neural and behavioral evidence for an online resetting process in visual working memory publication-title: J. Neurosci. doi: 10.1523/JNEUROSCI.2789-16.2016 – start-page: 254 year: 2020 ident: 10.1016/j.patcog.2024.111048_b12 article-title: Topology-preserving class-incremental learning – volume: 37 start-page: 3155 issue: 4 year: 2021 ident: 10.1016/j.patcog.2024.111048_b43 article-title: Parameter identification in power transmission systems based on graph convolution network publication-title: IEEE Trans. Power Deliv. doi: 10.1109/TPWRD.2021.3124528 |
| SSID | ssj0017142 |
| Score | 2.4744377 |
| Snippet | Federated learning is a distributed learning approach aimed at preserving user’s data privacy, while incremental learning is an adaptive machine learning... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 111048 |
| SubjectTerms | Federated learning Incremental learning Topological Data Analysis |
| Title | Federated Incremental Learning algorithm based on Topological Data Analysis |
| URI | https://dx.doi.org/10.1016/j.patcog.2024.111048 |
| Volume | 158 |
| WOSCitedRecordID | wos001331831600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 issn: 0031-3203 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0017142 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Pb9MwFLZg48AFxi8xYMgHbsgosZ3aOU5o0wbSNGlFKqfIjuMu00iqLkH983mO7TRjCAESl6iylLZ6X_L8-fnz9xB6Z6gQjM8smc1MRbiVhkipKCmNKTPLMy10MjSbEGdncrHIz0Ov9puhnYBoGrnZ5Kv_CjWMAdju6OxfwD1-KQzAZwAdrgA7XP8I-GNnD6EckYR331f_XLE6lkDU9bJd193lt_duAjNus2DuGyX4FKg6NTqVTJnr-WDE6Q6_BMXRdv_-pPe6jHoU8wSd78VlFSZGJ_mpQw1gualVO472Q632aw8I99MSBM2iajnWxeLZmK0Qaci1LCWMJuxWrvU-7Xfyti8hXH1YwfzTLmHZTrlL5ol34fzJEfvCG04mzkswEXnO76NdKrIcktru4enR4tO4jSRS7u3iw1-JZycHgd_d3_o1N5nwjfkeehQWCvjQA_wE3auap-hxbMKBQ05-hj6PeOMJ3jjijUe88YA3bhs8wRs7vHHE-zn6cnw0_3hCQocMUsJSsCNcW814XuaZ1dzOcqkroanQWZlam1FlUqZcK-bUJsaWKk8qYyHnwioWXspMS_YC7TRtU71EGKgjsDmmtWYlV1JJC0xFMguBNVQnah-RGJti5Y1QiqgQvCp8LAsXy8LHch-JGMAikDlP0grA_Ld3vvrnO1-jh9vH8w3a6dZ9dYAelN-7-mb9NjwcPwCn-3Fi |
| linkProvider | Elsevier |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Federated+Incremental+Learning+algorithm+based+on+Topological+Data+Analysis&rft.jtitle=Pattern+recognition&rft.au=Hu%2C+Kai&rft.au=Gong%2C+Sheng&rft.au=Li%2C+Lingxiao&rft.au=Luo%2C+Yuantu&rft.date=2025-02-01&rft.pub=Elsevier+Ltd&rft.issn=0031-3203&rft.volume=158&rft_id=info:doi/10.1016%2Fj.patcog.2024.111048&rft.externalDocID=S0031320324007994 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0031-3203&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0031-3203&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0031-3203&client=summon |