Differences

This shows you the differences between two versions of the page.

--- trans_learn:reading_group_2023 [2023/09/04 04:53] – wuyr
+++ trans_learn:reading_group_2023 [2023/10/23 10:47] (current) – wuyr
@@ Line 2: / Line 2: @@
 A biweekly reading group to discuss recent or classical papers on transfer learning methodologies and their applications on medical tasks. Other interesting theory topics are also welcomed.
-**Time:  Wednesday 8:30 p.m. (GMT+8)**
+**Time:  Monday 10:30 a.m. (GMT+8)**
 -----------------------------
-===04/11/2023===
+===04/12/2023===
   * Presenter: Wu Yanru
-  * Paper: Auxiliary Task Reweighting for Minimum-data Learning (Shi, 2020)
+  * Paper: Auxiliary Task Reweighting for Minimum-data Learning (Shi, NeurIPS 2020)
   * Slides: {{ :trans_learn:auxiliary_task_reweighting.pptx |}}
-===10/22/2021===
+===04/26/2023===
-  * Presenter: Liu Hanbing
+  * Presenter: Duan Shutong
-  * Paper: Optimal Transport for Domain Adaptation (Courty, 2016)
+  * A Brief Research in Semantic Segmentation with Multisource
-  * Slides:{{ :trans_learn:adversarial_discriminative_domain_adaptation.pptx |}}
+  * Slides:{{ :trans_learn:brief_literature_review.pptx |}}
-===10/29/2021===
+===05/10/2023===
-  * Presenter: Tong Xinyi
+  * Presenter: Zhao Zixi
-  * Paper: A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning (Tong, 2021)
+  * Paper: Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management (Song, IEEE Robotics and Automation Letters 2022)
-  * Slides: {{ :trans_learn:slides_xinyi1029.pdf |}}
+  * Slides: {{ :trans_learn:5.10_pre.pptx |}}
-===11/12/2021===
+===05/24/2023===
-  * Presenter: Wu Zhiyuan
+  * Presenter: Lai Jiahao
-  * Paper: Recasting gradient-based meta-learning as hierarchical bayes (Grant, 2018)
+  * Paper: Variational Continual Learning (Nguyen, ICLR 2018)
-  * Slides: {{ :trans_learn:zhiyuan_bayes_ml.pdf |}}
+  * Slides: {{ :trans_learn:5.24组会.pdf |}}
-===11/19/2021===
+===06/21/2023===
   * Presenter: Wu Yanru
-  * Paper: CDOT: Continuous Domain Adaptation using Optimal Transport (Guillermo, 2019)
+  * Paper: A Geometric Analysis of Neural Collapse with Unconstrained Features (Zhu and Ding, NeurIPS 2021)
-  * Slides: {{ :trans_learn:continuous_ot.pptx |}}
+  * Slides: {{ :trans_learn:a_geometric_analysis_of_neural_collapse_with.pptx |}}
----------------------------
+===07/05/2023===
+  * Presenter: Zhao Zixi
+  * Paper: Mad Max: Affine Spline Insights into Deep Learning (Balestriero, expanded from ICML 2018)
+  * Slides: {{ :trans_learn: 7.5_pre.pptx |}}
+===07/19/2023===
+  * Presenter: Dong Caixia
+  * Paper: High-quality coronary artery segmentation via fuzzy logic modeling coupled with dynamic graph convolutional network
+  * Slides: {{ :trans_learn: 冠脉分割20230802dcx.pdf |}}
+===08/02/2023===
+  * Presenter: Duan Shutong; Zhang Enming
+  * Paper: Discriminability and Transferability Estimation: A Bayesian Source Importance Estimation Approach for Multi-Source-Free Domain Adaptation (Han, AAAI 2023)
+  * Slides: {{ :trans_learn: date.pptx |}}
+===08/16/2023===
+  * Presenter 1: Wang Jingge
+  * Paper: TR-GAN: Multi-Session Future MRI Prediction With Temporal Recurrent Generative Adversarial Network (Fan, IEEE Transactions on Medical Imaging 2022)
+  * Slides: {{ :trans_learn: tr-gan_multi-session_future_mri_prediction_with_temporal_recurrent_generative_adversarial_network.pptx |}}
+  * Presenter 2: Zhao Zixi
+  * Paper: Max-Affine Spline Insights Into Deep Network Pruning (You and Balestriero, Transactions on Machine Learning Research 2022)
+  * Slides: {{ :trans_learn: 8.16_pre.pptx |}}
+===08/30/2023===
+  * Presenter 1: Yang Jingyun
+  * Paper: Pick the Best Pre-trained Model: Towards Transferability Estimation for Medical Image Segmentation (Yang, MICCAI 2023)
+  * Slides: {{ :trans_learn: rd.pdf |}}
+  * Presenter 2: Chen Xuechao
+  * Paper: Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts (Liu, ICLR 2023)
+  * Slides: {{ :trans_learn: paperreading20230830.pptx |}}
+===09/18/2023===
+  * Presenter 1: Xiangyu Chen
+  * Paper: Graph Neural Networks can Recover the Hidden Features Solely from the Graph Structure (Sato, ICML 2023)
+  * Slides: {{ :trans_learn: graph_recover.pptx |}}
+  * Presenter 2: Yanru Wu
+  * Paper: MATE: Plugging in Model Awareness to Task Embedding for Meta Learning (Chen and Wang, NeurIPS 2020)
+  * Slides: {{ :trans_learn: MATE.pptx |}}
+===10/11/2023===
+  * Presenter 1: Hanbing Liu
+  * Paper: Active Gradual Domain Adaptation: Dataset and Approach (Zhou, IEEE Transactions on Multimedia 2022)
+  * Slides: {{ :trans_learn: o |}}
+  * Presenter 2: Jiahao Lai
+  * Paper: Hypergraph Neural Networks (Feng, AAAI 2019)
+  * Slides: {{ :trans_learn: hypergnn.pdf |}}
+===10/23/2023===
+  * Presenter: Haohua Wang
+  * Paper: Fine-Tuning Language Models with Advantage-Induced Policy Alignment (Zhu, arXiv:2306.02231)
+  * Slides: {{ :trans_learn: fine-tuning_language_models_with_advantage-induced_policy_alignment_2_.pptx |}}
+-----------------------------