2022/10/24

• Attendee: Zhiyuan, Xiangyu, Yuanbo, Yang
• Meeting Summary

Xiangyu

• Xiangyu shared a instance normalization method for time-series forecasting against distribution shift which published in ICLR 2022.
  • 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-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.

2022/6/30

• Attendee: Zhiyuan, Xiangyu, Yang
• Meeting Summary:
  • Transcribe the matrixed-version formulation into its Lagrange version
  • Use gradient descend and integer projection to iteratively update the optimization problem
  • Interpretation and analysis the loss result of the proposed method
  • Regard the greedy algorithm as the supremum while the dynamic programming and real-relaxed optimization as the infimum and compute their approximation rate to measure the outcome with the optimal result
  • Integer rounding the result in real-domain by the hyper parameter threshold.
  • Make sure the application of the Pathlet is use a top-k dictionary to recomposite new trajectory and find how much information can be kept
• TO-DO:
  • Find the optimal threshold to integer round the real-domain solution, meaning we use matrix formulation to update result while guaranteeing the integer constraints
  • Find the application for the Pathlet in real-world project such as new coding for the spatial data

2022/06/08

• Attendee: Zhiyuan, Yuanbo, Yang
• Meeting Summary:
• Zhiyuan Peng:
  • Briefly introduce the general implementation of the dynamic programming with specific data structure.
  • Exemplify one trajectory results under different λ.
• Yuanbo Tang
  • Introduce the proposed algorithm in state machine term and analogues to the backpack problem in greedy thoughts (but need to connected to a specific math problem in order for its correctness)
  • Analyze and compare the result of proposed method with DP (including dictionary size and representation cost under different λ)
  • Use toy model to interpret the logic fallacy and disability to the optimal results
  • Based on finite map and sufficient trajectories, Transcribe the problem into matrix version
• TO-DO:
  • Survey on the linear restricted minmax convex optimization and whether the max option can be replaced?
  • Think the optimization in matrix version, proposed optimization algorithm version. Could it be connected with Markov decision process
  • If our model brings in more features, we can use NN.
  • Connect the proposed algorithm with some math problem like multi-armed bandit

2022/05/11

• Attendee: Zhiyuan, Xiangyu, Yang
• Meeting Summary:
  • Use package ‘pyechart’ in python to visualize the cumulative record amount in different h3 hexagon with data from XIAN
  • Implement LSTM on the processed data to predict the future record in each 5min time piece till 5 times
  • Prepare the PPT for opening report

• To-Do
  • Find the historical data construction used in literature，survey on how to jointly use long/short term data. We can use fusion or residue methods
  • Find the metrics to measure the prediction other than MSE, such as MAPE
  • For solution of the data sparsity and erratic, we can make a hybrid model.
    • First, we set a threshold to filter out those districts of historical average less than the threshold, and adopt a traditional statistical model
    • Second, we can use our multi-task DNN to predict other places.
    • At last, we can hybrid these two situations together
  • Find out the challenge and remedial algorithms

2022/03/09

• Attendee: Zhiyuan, Xiangyu, Yang
• Meeting Summary:
  • Zhiyuan: Share the LSTM+GCN overfitting problems, Yang gives some advice:
    • 1. Do more data mining in dataset such as visualize the prediction results and see the correlation about the closeness points in the graph.
  • Xiangyu: Show the results about META-MLP and MLP in UberNYC. Yang gives advice:
    • 1. Divide the task into weekdays and weekends looks like a cross-domain problem. In cross-domain problems, the pre-training method is often better than meta-learning, share the article about the cross-domain.
    • 2. Change the backbone network such as GCN to see the results.
  • Yang: Communicate with the Gaode group once every two weeks.

• To Do:
  • Zhiyuan and Yuanbo:
    • 1. Visualize the graph model prediction data and compare it with the ground truth using the hot map.
    • 2. Pre-training the LSTM then add the results into the GCN.
  • Xiangyu:
    • 1. Construct the few shot tasks: remove some weekends data to test the Meta-MLP and Pretraining.
    • 2. Add the baseline that uses the traditional time-series prediction method.
    • 3. Add more complex backbone models like GCN

2022/03/02

• Attendee: Zhiyuan and Yuanbo, Xiangyu, Yang
• Meeting Summary:
  • Discuss NYC taxi dataset(https://data.cityofnewyork.us/Transportation/NYC-Taxi-Zones/d3c5-ddgc): discuss the details about the datasets, pay attention to whether the pattern of ride-hailing data and taxi data is different.
  • Share related multi-task ride-hailing prediction papers.
  • Assigning pre-processing on dataset and trim the into an 8-days long slide window for region-based outflow prediction
  • Constructing a graph based on the closeness relationship among regions
  • Constructing a network based on a LSTM following with a GCN for predicting, but the loss function doesn’t converge.
  • Discuss the training of the base model. How to construct the graph construction of GCN and how to select the centroid? Is given by dataset. The training of GCN is no convergence.
  • Discuss the MLP+META compare with the pretraining method, try more metrics(MAE e.t.) and the task division method
  • Bayesian Graph Model: Read the paper “A Variational Bayesian Approach for Fast Adaptive Air Pollution Prediction”https://ieeexplore.ieee.org/document/9672075 Meta-learning under a Bayesian framework.PPT:https://cloud.tsinghua.edu.cn/f/0b7a4786c75c48108f72/

• TODO:
  • Drew the GCN network structure and have a discussion later.
  • Zhiyuan & Yuanbo:
    • We should do some explorative analysis on the data
    • Using heat map to observe if there exists convincing neighborhood similarity on the dataset
    • Using heat map to observe if GCN does smooth the discrepancy around neighborhoods and is it reasonable based on the ground truth
    • Analyze the pattern of the dataset and the detailed distribution of specific areas
    • Try to change the training session of the LSTM&GCN (can training solely on LSTM in the first few epochs)
  • Xiangyu:
    • Deduce how to variation in the bayesian meta-learning.
    • Try more methods in the task division methods in META-MLP.

2022/01/05

• Attendee: Yuanbo, Yang
• Meeting Summary:
  • Yuanbo reading: “MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction”https://arxiv.org/abs/1910.05449v1
  • Discussion about how to produce pathlet by NN or numerical method.https://ieeexplore.ieee.org/document/7293682
  • Discussion about how to predict trajectory using pathlet.

• TODO:
  • Yuanbo: deeper understanding of paper: figure out how the authors predict the trajectory and how they construct the Input representation.
  • Do some research on how to produce pathlet by NN and predict trajectory using pathlet.

2022/01/12

• Attendee: Yuanbo, Yang, Zhiyuan
• Meeting Summary:
  • Discussion about how to produce pathlet by NN using differentiable loss function.
  • Yuanbo propose one method which matches content and index between trajectories and candidate pathlets using slide windows.
  • The detailed info can be referred to this file: zhiyuan_2022_1_12

• TODO:
  • Yuanbo & Zhiyuan: Reimplement the proposed algorithm and do someexperiments on synthetic dataset, like fixed-pattern strings.