How to understand the network structure in this paper( a multiple timeseries fusion model )

Data Science Asked by Mithril on December 5, 2020

I want to implement this paper:

It has structure graph :
enter image description here

But I can’t understand how to generate Multiple Resolution Tensor R .

I understand all the steps except the detail of step 3:

  1. we have 3 time series when α, β ∈ {day : 1,week : 7} , so dr = 2

we can generate dr*(dr +1)/2 unique time series with different configurations of {⟨α, β⟩|α ∈ α, β ∈ β, α ≥ β} to represent multiple periodic time series distributions, in which dr = min(|α |, |β|).

  1. we need 3 gru/lstm to generate 3 hidden state with ds length

  2. Generate Multiple Resolution Tensor R

Inspired by these recent advances, we propose a convolutional fusion
framework to summarize a multi-resolution tensor $ R ∈ R^{|α |× |β |×ds} $ into a conclusive representation. Here we use R to represent a
collection of time-evolving patterns generated from multiple time
resolutions. Namely, $ R_{i,j,1:ds} $ denotes a learned sequence
pattern representation $ h_t^{αi, βj} $ at time t w.r.t. temporal
resolution αi and interval resolution βj as described in Eq. 2. We
further apply a mirror padding along the diagonal to complete the
tensor. The generation process of R is shown in Figure 1.(b).

  1. Apply CONV2D
  2. Apply CONV2D
  3. Apply FC

The ambiguous part is step 3 ! :

  1. For me, $ R ∈ R^{|α |× |β |×ds} $ shape is [dr*(dr +1)/2, ds] , so I have to add one dim to [dr*(dr +1)/2, ds, 1] to make it can be pass to conv2d , is this right ?
  2. But the Figure 1 write the ds (gru hidden state length) as channels , and it also draw the channels size has to be divide by 2 in every conv2d layer .

What is the correct way to generate Multiple Resolution Tensor R ?


I wrote a dummy model, you could reuse this :

import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

data = pd.DataFrame(np.random.uniform(size=(1000,3)), columns=['Sales', 'SalesDiff7', 'SalesAggMean7'])

multi_inputs = []
multi_outputs = []
window_size = k

for i in range(data.shape[1]):
    ti = keras.Input(shape=(window_size, 1), name=f't{i}')
    tlstm = layers.LSTM(32)(ti)
r = tf.stack(multi_outputs, axis=-2) 
r = tf.expand_dims(r, -1)  
conv1 = tf.keras.layers.Conv2D(filters=16,
                       kernel_size=(2, 2), #padding='same',
conv2 = tf.keras.layers.Conv2D(filters=8,
                       kernel_size=(2, 2), #padding='same',
fc = tf.keras.layers.Flatten()(conv1)
result = keras.layers.Dense(units=1)(fc)

Add your own answers!

Ask a Question

Get help from others!

© 2024 All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP