Questions tagged [embeddings]

184 questions
16
votes
2 answers

One Hot Encoding vs Word Embedding - When to choose one or another?

A colleague of mine is having an interesting situation, he has quite a large set of possibilities for a defined categorical feature (+/- 300 different values) The usual data science approach would be to perform a One-Hot Encoding. However, wouldn't…
11
votes
1 answer

Confusion about Entity Embeddings of Categorical Variables - Working Example!

Problem Statement: I have problem making the Entity Embedding of Categorical Variable works for a simple dataset. I have followed the original github, or paper, or other blogposts[1,2,or this 3], or this Kaggle kernel; still not working. Data Part:…
TwinPenguins
  • 4,157
  • 3
  • 17
  • 53
10
votes
2 answers

What is the difference between and Embedding Layer and an Autoencoder?

I'm reading about Embedding layers, especially applied to NLP and word2vec, and they seem nothing more than an application of Autoencoders for dimensionality reduction. Are they different? If so, what are the differences between them?
Leevo
  • 6,005
  • 3
  • 14
  • 51
9
votes
2 answers

Are there any graph embedding algorithms like this already?

I wrote an algorithm for generating node embeddings based on the graph's topology. Most of the explanation is done in the readme file and the examples. The question is: Am I reinventing the wheel? Does this approach have any practical advantages…
monomonedula
  • 201
  • 1
  • 2
8
votes
1 answer

Difference between Gensim word2vec and keras Embedding layer

I used the gensim word2vec package and Keras Embedding layer for various different projects. Then I realize they seem to do the same thing, they all try to convert a word into a feature vector. Am I understanding this properly? What exactly is the…
Edamame
  • 2,705
  • 5
  • 23
  • 32
7
votes
2 answers

Concatenating embedding and hand-designed features for logistic regression

An interviewer told me that we cannot concatenate an embedding from a neural network (such as a pre-trained image representation) and hand designed features (such as image metadata) for use in a linear model such as logistic regression. He says…
7
votes
1 answer

How much text is enough to train a good embedding model?

I need to train a word2vec embedding model on Wikipedia articles using Gensim. Eventually, I will use the entire Wikipedia for that but for the moment, I'm doing some experimentation/optimization to improve the model quality and I was wondering how…
6
votes
1 answer

What is the neural network architecture behind Facebook's Starspace model?

Recently, Facebook released a paper concerning a general purpose neural embedding model called StarSpace. In their paper, they explain the loss function and the training procedure of the model, but they don't emphasize much on the architecture of…
ChiPlusPlus
  • 545
  • 2
  • 5
  • 14
6
votes
1 answer

Unordered Input

I was just wondering what the best approach is for training a neural network (or any other machine learning algorithm) where the order of the inputs does not matter. For example: f(x1,x2,x3,x4) = f(x2,x1,x3,x4) = f(x2,x4,x1,x3) My current approach…
simeon
  • 173
  • 4
5
votes
1 answer

Tensorflow: how to look up and average a different amount of embedding vectors per training instance, with multiple training instances per minibatch?

In a recommender system setting: let's say I want to learn to predict future item purchases based on user past purchases using an approach inspired by Youtube's recommender system: Concretely, let's say I have a trainable content-based network that…
Pablo Messina
  • 377
  • 2
  • 10
4
votes
2 answers

Can we use embeddings or latent vectors for a recommender system?

I'm having a hard time understanding why people use any vector they find as a candidate for a recommender system. In my mind, a recommender system requires a space where distance represents similarity. Of course, before you can construct such a…
4
votes
1 answer

Why are character level models considered less effective than word level models?

I have read that character level models need more computation power than word embeddings, and this is one of the major reasons for their less effectiveness, but i got curious because the word embeddings need a huge vocabulary while character level…
yashdk
  • 41
  • 1
4
votes
1 answer

word2vec word embeddings creates very distant vectors, closest cosine similarity is still very far, only 0.7

I started using gensim's FastText to create word embeddings on a large corpus of a specialized domain (after finding that existing open source embeddings are not performing well on this domain), although I'm not using its character level n-grams, so…
4
votes
2 answers

Auto-Encoder to condense (pre-process) large one-hot input vectors?

In my 3D game there are 300 categories to which a creature can belong. I would like to teach my RL agent to make decisions based on its 10 closest monsters So far, my Neural Network input vector is a concatenation of ten 300-dimensional one-hot…
Kari
  • 2,686
  • 1
  • 17
  • 47
3
votes
0 answers

Combining heterogeneous numerical and text features

We want to solve a regression problem of the form "given two objects $x$ and $y$, predict their score (think about it as a similarity) $w(x,y)$". We have 2 types of features: For each object, we have about 1000 numerical features, mainly of the…
1
2 3
12 13