python - Compute the pairwise distance between each pair of the two collections of inputs in TensorFlow

Question

I have two collections. One consists of m₁ points in k dimensions and another one of m₂ points in k dimensions. I need to calculate pairwise distance between each pair of the two collections.

Basically having two matrices A_{m1, k} and B_{m2, k} I need to get a matrix C_{m1, m2}.

I can easily do this in scipy by using distance.sdist and select one of many distance metrics, and I also can do this in TF in a loop, but I can't figure out how to do this with matrix manipulations even for Eucledian distance.

Answer 1

After a few hours I finally found how to do this in Tensorflow. My solution works only for Eucledian distance and is pretty verbose. I also do not have a mathematical proof (just a lot of handwaving, which I hope to make more rigorous):

import tensorflow as tf
import numpy as np
from scipy.spatial.distance import cdist

M1, M2, K = 3, 4, 2

# Scipy calculation
a = np.random.rand(M1, K).astype(np.float32)
b = np.random.rand(M2, K).astype(np.float32)
print cdist(a, b, 'euclidean'), '
'

# TF calculation
A = tf.Variable(a)
B = tf.Variable(b)

p1 = tf.matmul(
    tf.expand_dims(tf.reduce_sum(tf.square(A), 1), 1),
    tf.ones(shape=(1, M2))
)
p2 = tf.transpose(tf.matmul(
    tf.reshape(tf.reduce_sum(tf.square(B), 1), shape=[-1, 1]),
    tf.ones(shape=(M1, 1)),
    transpose_b=True
))

res = tf.sqrt(tf.add(p1, p2) - 2 * tf.matmul(A, B, transpose_b=True))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    print sess.run(res)