Euclidean distance (norm of difference) and dot predict are [proportional to each other][1], so roughly the same: > After normalizing $a$ and $b$ such that$\|a\| = 1$ and $\|b\| = 1$, > these three measures are related as: > > Euclidean distance = $\| a - b \| = \sqrt{\| a \|^2 + \|b\|^2 - 2 a^Tb} =\sqrt{2 - 2 \cos(\theta_{ab})}$ > > Dot product = $\|a\|\|b\| \cos(\theta_{ab}) = 1 \cdot 1 \cdot \cos(\theta_{ab}) = \cos(\theta_{ab}) $ > > Cosine = $\cos(\theta_{ab})$ > > Thus, all three similarity measures are equivalent because they are > proportional to $\cos(\theta_{ab})$. as [also discussed in here][2]. There was even an empirical evaluation by [Qian et al (2004)][3] concluding that > Through our theoretical analysis and experimental results, we conclude > that EUD and CAD are similar when applied to high dimensional NN > queries. For normalized data and clustered data, EUD and CAD becomes > even more similar. [1]: https://developers.google.com/machine-learning/clustering/similarity/measuring-similarity [2]: https://skeptric.com/cosine-is-euclidean/ [3]: https://www.cse.msu.edu/~pramanik/research/papers/2003Papers/sac04.pdf