{"type":"ScholarlyArticle","title":"HyperFed: Hyperbolic Prototypes Exploration with Consistent Aggregation for Non-IID Data in Federated Learning","authors":[{"name":"Xinting Liao","slug":"xinting-liao","given":"Xinting","family":"Liao","affiliation":"College of Computer Science and Technology , Zhejiang University , Hangzhou , China"},{"name":"Weiming Liu","slug":"weiming-liu","given":"Weiming","family":"Liu","affiliation":"College of Computer Science and Technology , Zhejiang University , Hangzhou , China"},{"name":"Chaochao Chen","slug":"chaochao-chen","given":"Chaochao","family":"Chen","affiliation":"College of Computer Science and Technology , Zhejiang University , Hangzhou , China"},{"name":"Pengyang Zhou","slug":"pengyang-zhou","given":"Pengyang","family":"Zhou","affiliation":"College of Computer Science and Technology , Zhejiang University , Hangzhou , China"},{"name":"Huabin Zhu","slug":"huabin-zhu","given":"Huabin","family":"Zhu","affiliation":"College of Computer Science and Technology , Zhejiang University , Hangzhou , China"},{"name":"Yanchao Tan","slug":"yanchao-tan","given":"Yanchao","family":"Tan","affiliation":"College of Computer and Data Science , Fuzhou University , Fuzhou , China"},{"name":"Jun Wang","slug":"jun-wang","given":"Jun","family":"Wang","affiliation":"OPPO Research Institute , Shenzhen , China"},{"name":"Yue Qi","slug":"yue-qi","given":"Yue","family":"Qi","affiliation":"OPPO Research Institute , Shenzhen , China"}],"abstract":"Federated learning (FL) collaboratively models user data in a decentralized way. However, in the real world, non-identical and independent data distributions (non-IID) among clients hinder the performance of FL due to three issues, i.e., (1) the class statistics shifting, (2) the insufficient hierarchical information utilization, and (3) the inconsistency in aggregating clients. To address the above issues, we propose HyperFed which contains three main modules, i.e., hyperbolic prototype Tammes initialization (HPTI), hyperbolic prototype learning (HPL), and consistent aggregation (CA). Firstly, HPTI in the server constructs uniformly distributed and fixed class prototypes, and shares them with clients to match class statistics, further guiding consistent feature representation for local clients. Secondly, HPL in each client captures the hierarchical information in local data with the supervision of shared class prototypes in the hyperbolic model space. Additionally, CA in the server mitigates the impact of the inconsistent deviations from clients to server. Extensive studies of four datasets prove that HyperFed is effective in enhancing the performance of FL under the non-IID setting.","doi":"10.24963/ijcai.2023/440","url":"https://ijcai.org/proceedings/2023/440","pdf":"https://ijcai.org/proceedings/2023/0440.pdf","markdown":"https://ijcai.org/proceedings/2023/440.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/440","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":440,"pages":{"first":3957,"last":3965},"keywords":["Machine Learning: ML: Federated learning","Computer Vision: CV: Representation learning"],"videos":[],"references":[{"position":1,"raw":"EMNIST FMNIST Cifar10 Cifar100 Method \\NonIID Dir(0.1) Dir(0.5) Dir(5) Dir(0.1) Dir(0.5) Dir(5) Dir(0.1) Dir(0.5) Dir(5) Dir(0.1) Dir(0.5) Dir(5) FedAvg 88.86 92.86 93.31 78.51 86.75 88.75 36.82 62.44 67.53 27.61 29.26 30.12 FedProx 90.75 93.27 93.65 78.49 86.57 88.68 37.95 63.48 67.23 26.91 29.77 29.98 SCAFFOLD 90.35 93.38 93.70 79.20 87.03 88.80 33.10 66.99 70.53 29.57 33.25 33.86 FedDYN 91.30 92.63 93.13 85.25 89.46 90.51 35.16 65.07 69.04 29.16 31.49 32.21 MOON 91.97 93.50 93.91 83.78 90.27 91.08 33.54 60.23 62.45 22.86 24.49 25.99 Fed-RoD 89.42 92.80 93.52 77.26 89.17 90.78 37.79 66.90 70.81 17.06 24.32 31.99 FedBABU 86.34 91.95 92.74 74.31 82.44 85.21 37.90 60.11 65.16 22.98 24.56 23.89 SphereFed 93.25 93.93 94.07 88.55 90.55 91.17 32.41 70.02 70.13 22.37 24.96 24.72 HyperFed-Geodesic 93.35 94.13 94.43 79.00 90.76 91.48 34.26 65.53 68.65 26.05 29.07 26.62 HyperFed-Shared 93.82 93.98 94.16 85.29 90.48 91.23 36.44 69.21 73.16 33.62 35.31 36.30 HyperFed-Averaged 93.65 94.29 94.45 87.91 90.98 91.69 36.69 70.12 70.81 33.39 36.33 36.93 HyperFed 94.00 94.33 94.46 89.38 91.16 91.83 38.03 71.25 75.22 33.93 38.89 37.50 Table 1: G-FL accuracy (%) of the global model. We bold the best result. Dataset EMNIST FMNIST Cifar10 Cifar100 Method \\NonIID Dir(0.1) Dir(0.5) Dir(5) Dir(0.1) Dir(0.5) Dir(5) Dir(0.1) Dir(0.5) Dir(5) Dir(0.1) Dir(0.5) Dir(5) FedMTL 96.28 91.08 88.21 97.39 90.89 85.71 90.57 65.68 48.31 46.28 24.72 11.64 FedPer 97.23 94.19 92.97 96.87 90.54 87.21 91.93 75.63 67.20 49.69 32.75 23.89 pFedMe 97.23 94.03 92.62 96.03 88.57 84.95 92.45 77.64 66.09 55.20 36.34 28.19 Ditto 97.72 95.32 94.30 97.79 93.75 92.05 91.34 74.35 69.94 47.08 31.89 27.04 APPLE 97.19 94.08 92.63 96.79 90.49 86.59 89.85 67.96 56.13 42.94 24.61 20.39 Fed-RoD 97.76 95.31 93.99 97.21 93.48 91.62 91.24 72.11 71.33 35.03 27.70 32.22 FedBABU 97.36 94.17 92.81 96.64 89.59 85.57 92.04 64.05 63.46 29.30 25.05 24.01 SphereFed 93.61 94.11 94.34 88.91 90.87 91.88 91.68 78.39 72.86 40.68 32.63 34.90 HyperFed-Geodesic 97.97 95.60 94.48 97.00 93.98 91.89 91.68 72.20 69.02 29.70 27.11 27.03 HyperFed-Fixed 97.96 95.65 94.45 96.53 92.66 90.85 90.57 79.66 59.38 49.08 20.20 11.31 HyperFed-Shared 97.50 95.66 94.39 97.50 93.00 91.52 92.69 77.43 71.62 47.97 33.16 35.19 HyperFed-Averaged 97.71 95.13 94.46 97.83 93.73 91.96 92.63 70.53 69.02 53.50 36.49 35.79 HyperFed 98.76 96.11 94.53 98.13 94.19 92.08 93.49 83.17 74.94 59.85 40.94 36.80","title":"EMNIST FMNIST Cifar10 Cifar100 Method \\NonIID Dir(0.1) Dir(0.5) Dir(5) Dir(0.1) Dir","authors":null,"year":null,"venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Acar et al., 2020] Durmus Alp Emre Acar, Yue Zhao, Ra- mon Matas, Matthew Mattina, Paul Whatmough, and Venkatesh Saligrama. Federated learning based on dy- namic regularization. In ICLR, 2020.","title":"Federated learning based on dynamic regularization","authors":"Durmus Alp, Emre Acar, Yue Zhao, Ramon Matas, Matthew Mattina, Paul Whatmough, Venkatesh Saligrama","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Arivazhagan et al., 2019] Manoj Ghuhan Arivazhagan, Vinay Aggarwal, Aaditya Kumar Singh, and Sunav Choudhary. Federated learning with personalization layers. arXiv preprint arXiv:1912.00818, 2019.","title":"Federated learning with personalization layers","authors":"Vinay Manoj Ghuhan Arivazhagan, Aaditya Kumar Aggarwal, Sunav Singh, Choudhary","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bonnabel, 2013] Silvere Bonnabel. Stochastic gradient de- scent on riemannian manifolds. IEEE Transactions on Au- tomatic Control, 58(9):2217-2229, 2013.","title":"Stochastic gradient descent on riemannian manifolds","authors":"Silvere Bonnabel","year":"2013","venue":"IEEE Transactions on Automatic Control","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen and Chao, 2021] Hong-You Chen and Wei-Lun Chao. On bridging generic and personalized federated learning for image classification. In ICLR, 2021.","title":"On bridging generic and personalized federated learning for image classification","authors":"Chen, Chao ; Hong-You Chen, Wei-Lun Chao","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2022a] Chaochao Chen, Jun Zhou, Longfei Zheng, Huiwen Wu, Lingjuan Lyu, Jia Wu, Bingzhe Wu, Ziqi Liu, Li Wang, and Xiaolin Zheng. Vertically federated graph neural network for privacy-preserving node classifi- cation. In IJCAI, pages 1959-1965. ijcai.org, 2022.","title":"Vertically federated graph neural network for privacy-preserving node classification","authors":"Chen","year":"2022","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2022/272"},{"position":7,"raw":"[Chen et al., 2022b] Weize Chen, Xu Han, Yankai Lin, Hexu Zhao, Zhiyuan Liu, Peng Li, Maosong Sun, and Jie Zhou. Fully hyperbolic neural networks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pages 5672-5686, 2022.","title":"Fully hyperbolic neural networks","authors":"Chen","year":"2022","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Cho et al., 2019] Hyunghoon Cho, Benjamin DeMeo, Jian Peng, and Bonnie Berger. Large-margin classification in hyperbolic space. In PMLR, pages 1832-1840. PMLR, 2019.","title":"Large-margin classification in hyperbolic space","authors":"Cho","year":"2019","venue":"PMLR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Cohen et al., 2017] Gregory Cohen, Saeed Afshar, Jonathan Tapson, and Andre Van Schaik. Emnist: Extending mnist to handwritten letters. In IJCNN, pages 2921-2926. IEEE, 2017.","title":"Emnist: Extending mnist to handwritten letters","authors":"Gregory Cohen, Saeed Afshar, Jonathan Tapson, Andre Van Schaik","year":"2017","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Désidéri, 2012] Jean-Antoine Désidéri. Multiple-gradient descent algorithm (mgda) for multiobjective optimization. Comptes Rendus Mathematique, 350(5-6):313-318, 2012.","title":"Multiple-gradient descent algorithm (mgda) for multiobjective optimization","authors":"Jean-Antoine Désidéri","year":"2012","venue":"Comptes Rendus Mathematique","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dong et al., 2022] Xin Dong, Sai Qian Zhang, Ang Li, and HT Kung. Spherefed: Hyperspherical federated learning. In ECCV, pages 165-184. Springer, 2022.","title":"Spherefed: Hyperspherical federated learning","authors":"Xin Dong, Qian Sai, Ang Zhang, Li, Kung","year":"2022","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ermolov et al., 2022] Aleksandr Ermolov, Leyla Mir- vakhabova, Valentin Khrulkov, Nicu Sebe, and Ivan Oseledets. Hyperbolic vision transformers: Combining improvements in metric learning. In CVPR, pages 7409-7419, 2022.","title":"Hyperbolic vision transformers: Combining improvements in metric learning","authors":"Aleksandr Ermolov, Leyla Mirvakhabova, Valentin Khrulkov, Nicu Sebe, Ivan Oseledets","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Fallah et al., 2020] Alireza Fallah, Aryan Mokhtari, and Asuman Ozdaglar. Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach. NeurIPS, 33:3557-3568, 2020.","title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","authors":"Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ganea et al., 2018] Octavian Ganea, Gary Bécigneul, and Thomas Hofmann. Hyperbolic entailment cones for learn- ing hierarchical embeddings. In ICML, pages 1646-1655.","title":"Hyperbolic entailment cones for learning hierarchical embeddings","authors":"Ganea","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"PMLR, 2018.","title":null,"authors":"Pmlr","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ghadimi Atigh et al., 2021] Mina Ghadimi Atigh, Martin Keller-Ressel, and Pascal Mettes. Hyperbolic busemann learning with ideal prototypes. NeurIPS, 34:103-115, 2021.","title":"Mina Ghadimi Atigh, Martin Keller-Ressel, and Pascal Mettes. Hyperbolic busemann learning with ideal prototypes","authors":"Ghadimi Atigh","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"He","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Hsu et al., 2019] Tzu-Ming Harry Hsu, Hang Qi, and Matthew Brown. Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335, 2019.","title":"Measuring the effects of non-identical data distribution for federated visual classification","authors":"Hsu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Jaggi, 2013] Martin Jaggi. Revisiting frank-wolfe: Projection-free sparse convex optimization. In ICML, pages 427-435.","title":"Revisiting frank-wolfe: Projection-free sparse convex optimization","authors":"Martin Jaggi, Jaggi","year":"2013","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"PMLR, 2013.","title":null,"authors":"Pmlr","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Karimireddy et al., 2019] Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank J Reddi, Sebas- tian U Stich, and Ananda Theertha Suresh. Scaffold: Stochastic controlled averaging for on-device federated learning. In ICML. PMLR, 2019.","title":"Scaffold: Stochastic controlled averaging for on-device federated learning","authors":"Praneeth Sai, Satyen Karimireddy, Mehryar Kale, Mohri, J Sashank, Sebastian U Reddi, Ananda Stich, Suresh Theertha","year":"2019","venue":"ICML. PMLR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Khrulkov et al., 2020] Valentin Khrulkov, Leyla Mir- vakhabova, Evgeniya Ustinova, Ivan Oseledets, and Victor Lempitsky. Hyperbolic image embeddings. In CVPR, pages 6418-6428, 2020.","title":"Hyperbolic image embeddings","authors":"Valentin Khrulkov, Leyla Mirvakhabova, Evgeniya Ustinova, Ivan Oseledets, Victor Lempitsky","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Krizhevsky et al., 2009] Alex Krizhevsky, Geoffrey Hinton, et al. Learning multiple layers of features from tiny im- ages. Technical Report, University of Toronto, 2009.","title":"Learning multiple layers of features from tiny images","authors":"Alex Krizhevsky, Geoffrey Hinton","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[LeCun et al., 1998] Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning ap- plied to document recognition. Proceedings of the IEEE, 86(11):2278-2324, 1998.","title":"Gradient-based learning applied to document recognition","authors":"Yann Lecun, Léon Bottou, Yoshua Bengio, Patrick Haffner","year":"1998","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Li et al., 2019] Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, and Zhihua Zhang. On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189, 2019.","title":"On the convergence of fedavg on non-iid data","authors":"Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, Zhihua Zhang","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Li et al., 2020] Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. Federated optimization in heterogeneous networks. Pro- ceedings of Machine Learning and Systems, 2:429-450, 2020.","title":"Federated optimization in heterogeneous networks","authors":"Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith","year":"2020","venue":"Proceedings of Machine Learning and Systems","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Li et al., 2021a] Qinbin Li, Bingsheng He, and Dawn Song. Model-contrastive federated learning. In CVPR, pages 10713-10722, 2021.","title":"Bingsheng He, and Dawn Song. Model-contrastive federated learning","authors":"Li","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Li et al., 2021b] Tian Li, Shengyuan Hu, Ahmad Beirami, and Virginia Smith. Ditto: Fair and robust federated learn- ing through personalization. In ICML, pages 6357-6368. PMLR, 2021.","title":"Ditto: Fair and robust federated learning through personalization","authors":"Li","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Linial et al., 1995] Nathan Linial, Eran London, and Yuri Rabinovich. The geometry of graphs and some of its al- gorithmic applications. Combinatorica, 15(2):215-245, 1995.","title":"The geometry of graphs and some of its algorithmic applications","authors":"Linial","year":"1995","venue":"Combinatorica","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Liu et al., 2019] Qi Liu, Maximilian Nickel, and Douwe Kiela. Hyperbolic graph neural networks. NeurIPS, 32, 2019.","title":"Hyperbolic graph neural networks","authors":"Liu","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Liu et al., 2020] Shaoteng Liu, Jingjing Chen, Liangming Pan, Chong-Wah Ngo, Tat-Seng Chua, and Yu-Gang Jiang. Hyperbolic visual embedding learning for zero-shot recognition. In CVPR, pages 9273-9281, 2020.","title":"Hyperbolic visual embedding learning for zero-shot recognition","authors":"Liu","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Liu et al., 2021] Weiming Liu, Jiajie Su, Chaochao Chen, and Xiaolin Zheng. Leveraging distribution alignment via stein path for cross-domain cold-start recommendation. In NeurIPS, pages 19223-19234, 2021.","title":"Leveraging distribution alignment via stein path for cross-domain cold-start recommendation","authors":"Weiming Liu, Jiajie Su, Chaochao Chen, Xiaolin Zheng","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Liu et al., 2023] Weiming Liu, Xiaolin Zheng, Chaochao Chen, Jiajie Su, Xinting Liao, Mengling Hu, and Yanchao Tan. Joint internal multi-interest exploration and external domain alignment for cross domain sequential recommen- dation. In WWW, page 383-394, New York, NY, USA, 2023. Association for Computing Machinery.","title":"Joint internal multi-interest exploration and external domain alignment for cross domain sequential recommendation","authors":"Weiming Liu, Xiaolin Zheng, Chaochao Chen, Jiajie Su, Xinting Liao, Mengling Hu, Yanchao Tan","year":"2023","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Luo and Wu, 2021] Jun Luo and Shandong Wu. Adapt to adaptation: Learning personalization for cross-silo feder- ated learning. arXiv preprint arXiv:2110.08394, 2021.","title":"Adapt to adaptation: Learning personalization for cross-silo federated learning","authors":"Wu Luo, Jun Luo, Shandong Wu","year":"2021","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2022/301"},{"position":35,"raw":"[Luo et al., 2022] Zhengquan Luo, Yunlong Wang, Zilei Wang, Zhenan Sun, and Tieniu Tan. Disentangled fed- erated learning for tackling attributes skew via invariant aggregation and diversity transferring. In ICML, volume 162 of Proceedings of Machine Learning Research, pages 14527-14541. PMLR, 2022.","title":"Disentangled federated learning for tackling attributes skew via invariant aggregation and diversity transferring","authors":"Luo","year":"2022","venue":"Proceedings of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[McInnes et al., 2018] Leland McInnes, John Healy, and James Melville. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.","title":"Umap: Uniform manifold approximation and projection for dimension reduction","authors":"Mcinnes","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[McMahan et al., 2017] Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Ar- cas. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273-1282. PMLR, 2017.","title":"Communication-efficient learning of deep networks from decentralized data","authors":"Brendan Mcmahan, Eider Moore, Daniel Ramage, Seth Hampson, Blaise Aguera Y Arcas","year":"2017","venue":"Artificial intelligence and statistics","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Mettes et al., 2019] Pascal Mettes, Elise van der Pol, and Cees Snoek. Hyperspherical prototype networks. NeurIPS, 32, 2019.","title":"Hyperspherical prototype networks","authors":"Mettes","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Movshovitz-Attias et al., 2017] Yair Movshovitz-Attias, Alexander Toshev, Thomas K Leung, Sergey Ioffe, and Saurabh Singh. No fuss distance metric learning using proxies. In CVPR, pages 360-368, 2017.","title":"No fuss distance metric learning using proxies","authors":"Movshovitz-Attias","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Nickel and Kiela, 2017] Maximillian Nickel and Douwe Kiela. Poincaré embeddings for learning hierarchical rep- resentations. NeurIPS, 30, 2017.","title":"Maximillian Nickel and Douwe Kiela. Poincaré embeddings for learning hierarchical representations","authors":"Kiela Nickel","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"Oh et al., ] Jaehoon Oh, SangMook Kim, and Se-Young Yun. Fedbabu: Toward enhanced representation for fed- erated image classification. In ICLR, 2021.","title":"Fedbabu: Toward enhanced representation for federated image classification","authors":"Oh","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Sekitani and Yamamoto, 1993] Kazuyuki Sekitani and Yoshitsugu Yamamoto. A recursive algorithm for finding the minimum norm point in a polytope and a pair of clos- est points in two polytopes. Mathematical Programming, 61(1):233-249, 1993.","title":"A recursive algorithm for finding the minimum norm point in a polytope and a pair of closest points in two polytopes","authors":"Yamamoto Sekitani, Kazuyuki Sekitani, Yoshitsugu Yamamoto","year":"1993","venue":"Mathematical Programming","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Sener and Koltun, 2018] Ozan Sener and Vladlen Koltun. Multi-task learning as multi-objective optimization. Ad- vances in neural information processing systems, 31, 2018.","title":"Multi-task learning as multi-objective optimization","authors":"Koltun ; ] Ozan Sener, Vladlen Sener, Koltun","year":"2018","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Shen et al., 2021] Jiayi Shen, Zehao Xiao, Xiantong Zhen, and Lei Zhang. Spherical zero-shot learning. IEEE Trans- actions on Circuits and Systems for Video Technology, 32(2):634-645, 2021.","title":"Spherical zero-shot learning","authors":"Jiayi Shen, Zehao Xiao, Xiantong Zhen, Lei Zhang","year":"2021","venue":"IEEE Transactions on Circuits and Systems for Video Technology","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Shimizu et al., 2020] Ryohei Shimizu, Yusuke Mukuta, and Tatsuya Harada. Hyperbolic neural networks++. arXiv preprint arXiv:2006.08210, 2020.","title":"Hyperbolic neural networks++","authors":"Ryohei Shimizu, Yusuke Mukuta, Tatsuya Harada","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Smith et al., 2017] Virginia Smith, Chao-Kai Chiang, Maziar Sanjabi, and Ameet S Talwalkar. Federated multi-task learning. NeurIPS, 30, 2017.","title":"Federated multi-task learning","authors":"Smith","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[T Dinh et al., 2020] Canh T Dinh, Nguyen Tran, and Josh Nguyen. Personalized federated learning with moreau en- velopes. NeurIPS, 33:21394-21405, 2020.","title":"Personalized federated learning with moreau envelopes","authors":"Nguyen Canh T Dinh, Josh Tran, Nguyen","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Tammes, 1930] Pieter Merkus Lambertus Tammes. On the origin of number and arrangement of the places of exit on the surface of pollen-grains. Recueil des travaux botaniques néerlandais, 27(1):1-84, 1930.","title":"On the origin of number and arrangement of the places of exit on the surface of pollen-grains","authors":"Pieter Merkus, Lambertus Tammes","year":"1930","venue":"Recueil des travaux botaniques néerlandais","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Tan et al., 2022a] Alysa Ziying Tan, Han Yu, Lizhen Cui, and Qiang Yang. Towards personalized federated learn- ing. IEEE Transactions on Neural Networks and Learning Systems, 2022.","title":"Towards personalized federated learning","authors":"Tan","year":"2022","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Tan et al., 2022b] Yanchao Tan, Carl Yang, Xiangyu Wei, Chaochao Chen, Longfei Li, and Xiaolin Zheng. Enhanc- ing recommendation with automated tag taxonomy con- struction in hyperbolic space. In ICDE, pages 1180-1192. IEEE, 2022.","title":"Enhancing recommendation with automated tag taxonomy construction in hyperbolic space","authors":"Tan","year":"2022","venue":"ICDE","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Weber et al., 2020] Melanie Weber, Manzil Zaheer, Ankit Singh Rawat, Aditya K Menon, and Sanjiv Ku- mar. Robust large-margin learning in hyperbolic space. NeurIPS, 33:17863-17873, 2020.","title":"Robust large-margin learning in hyperbolic space","authors":"Melanie Weber, Manzil Zaheer, Ankit Singh Rawat, Aditya K Menon, Sanjiv Kumar","year":"2020","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Xiao et al., 2017] Han Xiao, Kashif Rasul, and Roland Vollgraf. Fashion-mnist: a novel image dataset for bench- marking machine learning algorithms. arXiv preprint arXiv:1708.07747, 2017.","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","authors":"Xiao","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Zhao et al., 2018] Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, and Vikas Chandra. Fed- erated learning with non-iid data. arXiv preprint arXiv:1806.00582, 2018.","title":"Federated learning with non-iid data","authors":"Yue Zhao, Meng Li, Liangzhen Lai, Naveen Suda, Damon Civin, Vikas Chandra","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}