Differences

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

--- mobility_data:top [2022/10/24 04:49] – xianggyuchen
+++ mobility_data:top [2022/10/24 09:24] (current) – [Meeting Note] zhiyuanpeng
@@ Line 7: / Line 7: @@
   Xiangyu
   * Xiangyu shared a instance normalization method for time-series forecasting against distribution shift which published in ICLR 2022.
-    * The MSE of MLP for gaode's dataset(350days training data,50days test data) is improved from 4.65 to 3.26( 30%+).
+    * Using this method the MSE of MLP for gaode's dataset(350days training data,50days test data) improved from 4.65 to 3.26( 30%+).
-    * Next step I will implement this method in our meta-learning framewrok to see the improvements and compare the effiectiveness of our method and the normalization.[Presentation-slicdes:https://cloud.tsinghua.edu.cn/f/75320708a08f404e8a0b/]
+    * Next step I will implement this method in our meta-learning framewrok to see the improvements and compare the effiectiveness of our method and the normalization.[Presentation-slides:https://cloud.tsinghua.edu.cn/f/75320708a08f404e8a0b/]
+* Zhiyuan
+  * Summary:
+    * this week, I conducted a series of experiments to compare our Soft-restricted MF Multi-task learning model performance with single loss trained ones.
+    * This weeks experiments reveal that the multitask loss only contributes limitedly to the improvement on the both two tasks.
+    * Moreover, the LSTM based backbone tends to predict more smoother compared to the more fluctuated data in reality.
+    * An important observation: MSE mainly comes from several regions that has great volatility.
+  * Future Plan:
+    * Maybe next week we can try to use multi-source input data or time sequence analysis method to deal with it.
 /6/30