minfanphd的博客

分享对论文的理解, 原文见 Jérome Simon, Gabriel Fabien-Ouellet, Erwan Gloaguen, and Ishan Khurjekar, Hierarchical transfer learning for deep learning velocity model building, Geophysics, 2003, R79–R93. 这次的层次迁移应该指从 1D 到 2D 再到 3D.

分享对论文的理解, 原文见 Gabriel Fabien-Ouellet and Rahul Sarkar, Seismic velocity estimation: A deep recurrent neural-network approach. Geophysics (2020) U21--U29. 作者应该是领域专家, 对地球科学的理解胜于深度学习. 为方便讨论, 等式编号保持与原文一致.

分享对论文的理解, 原文见 Xi Peng, Yunfan Li, Ivor W. Tsang, Hongyuan Zhu, Jiancheng Lv, Joey Tianyi Zhou,XAI Beyond Classification: Interpretable Neural Clustering, Journal of Machine Learning Research 22 (2021) 1--27.

摘要: 分享对论文的理解, 原文见 Peng Jin, Xitong Zhang, Yinpeng Chen, Sharon Xiaolei Huang, Zicheng Liu, Youzuo Lin, Unsupervised learning of full-waveforminversion: connecting CNN and partial differential equation in a loop.

摘要: 分享对论文的理解, 原文见 Zhongping Zhang and Youzuo Lin, Data-driven seismic waveform inversion: A study on the robustness and generalization.

摘要: 本文描述对论文 Murat Sensoy, Lance Kaplan, Melih Kandemir, Evidential deep learning to quantify classification uncertainty, NIPS 2018 的理解.

摘要: 深度学习做地震数据反演的一些文献综述. 组内分享, 会不断充实.

摘要: 分享对论文的理解, 原文见 Yashoteja Prabhu and Manik Varma, FastXML: A Fast, Accurate and Stable Tree-classifier for eXtreme Multi-label Learning.

摘要: 描述对极限多标签学习的基本理解, 包括数据特点、应用领域、评价指标、算法流派等.

摘要: 分享对论文的理解. 原文见 Jason Davis, Brian Kulis, Suvrit Sra and Inderjit Dhillon, Information-Theoretic Metric Learning, ICML 2007. 只有可怜的 5 页, 但引用达到 2000 余次.

摘要: 分享对论文的理解. 原文见 Kilian Q. Weinberger, John Blitzer and Lawrence K. Saul, Distance Metric Learning for Large Margin Nearest Neighbor Classification, NIPS 2005.

摘要: 度量学习的基本思想是将数据映射到一个新空间, 使得同一类别的数据更相近, 不同类别的数据更容易区分.

摘要: 分享对论文的理解. 原文见 X. Wang et al., KGAT: Knowledge Graph Attention Network for Recommendation, KDD 2019.

摘要: 分享对论文的理解. 原文见 Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio, Graph attention networks, ICLR 2018, 1--12. 可以在 ArXiv: 1710.10903v3 下载. 完全难以估计影响力有多大!......

摘要: 分享对论文的理解. 原文见 D. Saini, A. K. Jain, K. Dave, J. Jiao, A. Singh, R. Zhang and M. Varma, GalaXC: Graph neural networks with labelwise attention for extreme classification, in WWW 2021.

摘要: 分享对论文的理解. 原文见 Zhang, J., Li, S., Jiang, M., & Tan, K. C. (2020). Learning from weakly labeled data based on manifold regularized sparse model. IEEE Transactions on Cybernetics, (pp. 1--14).

摘要: 分享对论文的理解. 原文见 Akbarnejad, A. H., & Baghshah, M. S. (2019). An efficient semi-supervised multi-label classifier capable of handling missing labels. IEEE Transactions on Knowledge and Data Engineering, 31, 229--242.

摘要: 分享对论文的理解. 原文见 Ma, Z.-C., & Chen, S.-C. (2021). Expand globally, shrink locally: Discrimi-nant multi-label learning with missing labels. Pattern Recognition, 111, 107675.

摘要: 分享对论文的理解. 原文见 Huang, J., Qin, F., Zheng, X., Cheng, Z.-K., Yuan, Z.-X., Zhang, W.-G., & Huang, Q.-M. (2019). Improving multi-label classification with missing labels by learning label-specific features. Information Sciences, 492, 124--146.............

摘要: 分享对论文的理解. 原文见 Xie, M.-K., & Huang, S.-J. (2022). Partial multi-label learning with noisy label identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 1--12.

摘要: 分享对论文的理解. 原文见 Wang, R., Kwong, S., Wang, X., & Jia, Y. (2021). Active k-labelsets ensemble for multi-label classification. Pattern Recognition, 109, 107583.

摘要: 解读论文《基于一种改进凸集投影方法的地震数据同时插值和去噪》, 地球物理学报, 2015(8): 2935--2947.

摘要: 论文提出一种挖掘 "surprise pattern" 的方法. 我应张老板的要求, 在这里对符号系统进行纠错.

摘要: 分享对论文的理解. 原文见 Zhang, M.-L., & Wu, L. (2014). LIFT: Multi-label learning with label-specific features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 107--120.

摘要: 分享对论文的理解. 原文见 Zhang, M.-L., & Zhou, Z.-H. (2006). Multi-label neural networks with applications to functional genomics and text categorization. IEEE transactions on Knowledge and Data Engineering, 18, 1338--1351.

摘要: 分享对论文的理解. 原文见 Yue Zhu, James T. Kwok, Zhi-Hua Zhou, Multi-Label Learning with Global and Local Label Correlation, IEEE Transactions on Knowledge and Data Engineering, 2018 (30), 1081–1094.

论文题目: Improve Computer-Aided Diagnosis With Machine Learning Techniques Using Undiagnosed Samples论文优势: 几个概念在当时比较新.论文劣势 (现在的观点): 数据集太小，方法比较简单.可以作为我们工作的比较算法.Why semi-supervised?Unlabeled data can help improving the performance of the learner.Why co-tr

Context-Aware Recommender System Based on Boolean Matrix Factorisation1.1 使用了 BMF-based approach 这个说法.An FCA-based Boolean Matrix Factorisation for Collaborative Filtering2.1 使用了 based on Boolean Matrix Factorisation (BMF) and Formal Concept Analysi..

原文: Jian Wu 等. Multi-Label Active Learning Algorithms for Image Classification: Overview and Future Promise, ACM Computing Surveys, Vol. 53, No. 2, Article 28. Publication date: March 2020我报着学习与研讨的态度来写贴子, 难免与原作者的观点有诸多不同, 并没有不尊重原作者的意思.AbstractThese algo