Questions tagged [embeddings]
For questions about embeddings (not necessarily just word embeddings, for which there is a specific tag) in the context of machine learning.
65
questions
0
votes
0
answers
16
views
Improving embedding similarity search of aggregated embeddings
I am building an author suggestion tool that proposes authors writing about similar topics as a given input text. I want to use embeddings for this. The way I currently do it is to store embeddings of ...
0
votes
2
answers
42
views
How do I choose a good treshold for classification (using cosine similarity scores)?
I am using openai's text-embedding-ada-002 embeddings model to do a semantic search on a database of articles to find articles that are most related to a given ...
2
votes
0
answers
88
views
Nearest neighbour search in high dimension retrieves certain points too often
We represent some catalogue items (documents, music tracks, videos, whatever) as vectors embedded in R^d and use them to retrieve nearest neighbours to users query. The typical scenario is that users ...
0
votes
0
answers
86
views
How can I send vectors as a chat context?
Since the context/memory of a chat or question for LLMs more precisely GPT is limited to a token length I struggle about how to provide own data that the model got not trained on.
A very common ...
0
votes
0
answers
10
views
How to inspect a dimension in SBERT embeddings
I am using SBERT transformers to vectorize text. I want to use the sentence embeddings in a linear regression to predict a value or a classification. Some dimensions are highly colinear and result in ...
0
votes
1
answer
42
views
What do different embedding functions do?
Embeddings are just arrays of numbers that represent some data (sentences or images). How do embedding functions differ. For example what advantage does OpenAI's embeddings API have over others?
0
votes
0
answers
12
views
How to perform graph embedding on a DAG graph with point weights and restore the resulting embedding vector to the DAG with point weights?
How to perform graph embedding on a directed acyclic graph with point weights and restore the resulting embedding vector to the directed acyclic graph with point weights?
1
vote
0
answers
27
views
Is the input embedding split along the embedding dimension so that every head of the multi-head-attention module just gets a part of the input data?
So I found two contradictory explanations of the MHA (multi-head-self-attention-module):
In the first approach, the input embedding (= the input matrix) is split along the embedding dimension and all ...
1
vote
1
answer
242
views
Creating a support chat bot for my business
I am trying to create a kind of Support Bot to answer my clients about specific technical details about WordPress plugins that I sell.
The goal is that the /completitions api would be feeded a prompt ...
0
votes
0
answers
14
views
How does FaceNet (or similar) bootstrap new faces?
In a metric learning system the system can be trained on known examples such that common classes (faces) are clustered together and separated from each other as much as possible. If triplet loss is ...
0
votes
0
answers
16
views
Does attention in transformers encode any information from positional embeddings?
I know we account for positional embeddings before feeding into attention layers, but would we be able to say that the Q and K dot products intrinsically encode relative positions
0
votes
0
answers
23
views
How to evaluate output of text generation models?
Evaluation of a wide variety of natural language generation (NLG) tasks is difficult. For instance, for a question answering model, it is hard for a human to quantify how well the model has answered a ...
0
votes
0
answers
49
views
How do you specify the dimension to search for similarity in CLIP image embeddings?
I have a question about CLIP semantic image search. When you have an image of a person e.g. a skinny person wearing red shirt, clip will search for you similarity in all dimensions including body ...
0
votes
0
answers
49
views
Using a VQ-VAE encoder's output to condition another model
I've trained a VQ-VAE on images that I want to use to condition another model (latent diffusion). The shape of my encoder's output is (4, 256, 56, 56) and I'm getting it using:
...
0
votes
0
answers
14
views
Is it a problem if the target network and main network are the same?
I am currently working with this code that I found on Github: this is a DQN with Graph Neural Network (GNN) on TSP problem.
So, in this architecture, the target network and the main network are the ...
0
votes
0
answers
10
views
How to embed ordered integer values in a hidden layer
I want to embed integer positive values (ranging from 1 to 10000), which are ordered and not categorical, i.e., 1 is near to 2 than to 1000. This representation should be combined with numerical ...
0
votes
0
answers
107
views
How do transformers handle multidimensional input?
Transformers work with lists of vectors, i.e. sentence of length SEQ_LEN, with each word having size EMBEDDING_DIM. Now, since the model still makes use of Dense layers internally, i.e. as in https://...
0
votes
1
answer
104
views
Are there methods which represent entire knowledge graphs in one embedding vector?
In a knowledge graph, embedding vectors can be learned for nodes (node embedding) and edges (edge embeddings). Is there a method to learn one single embedding vector for the entire knowledge graph?
0
votes
0
answers
18
views
What's a good regression algorithm for handling tabular data that have categorical data, "list of words"
Problem statement: I want to predict future prices of trips based on historical pricing data.
I'm looking for an algorithm that has the following features:
Unsupervised algorithm
Limit the amount of ...
0
votes
1
answer
208
views
How to get meaningful vector embeddings for (lat, long) points and also GPS trajectories?
I have a data that consists of approx. 1.5M taxi trips in Porto, Portugal. (from: https://www.kaggle.com/competitions/pkdd-15-taxi-trip-time-prediction-ii/overview) Each of these trips have it's GPS ...
0
votes
0
answers
57
views
Embedding layers/entities in openAI's Hide and seek paper
I've recently come across a youtube video about openAI's hide and seek paper (https://openai.com/blog/emergent-tool-use/) and got really fascinated about the paper itself. But as I digging in the ...
0
votes
0
answers
4
views
Are there standard token vocabularies for text encoding?
Are there good standard token vocabularies for text encoding tasks? I am looking for a set of syllables and letters, and maybe some very common words, in the best case sorted by frequency.
If possible,...
1
vote
0
answers
79
views
Privacy implications of storing and transmitting GPT-3 embeddings?
We are exploring implementing a feature where a user might enter "which product has optional all wheel drive" into a search input, which would be transformed to GPT-3 embeddings, and ...
1
vote
0
answers
52
views
Use multiple embeddings with the Transformer architecture
In their article about their system "MuseNet" OpenAI state the following:
Embeddings
We added several different kinds of embeddings to give the model more
structural context. In addition to ...
0
votes
0
answers
53
views
How to evaluate the embeddings of a model?
If you have a task of extracting embeddings from a model (such as penultimate layer - pre-last layer of the model), would you train the model on a benchmark similar dataset (if there were) or train on ...
1
vote
1
answer
66
views
How to embed quantitative variables?
I have 3 data types that I want to feed into a neural net.
One, is a time series, which I am going to feed into the neural net directly. The second, are categorical variables that I am going to embed ...
0
votes
0
answers
14
views
Pose Sequence embedding
I am using a pose detection software which returns pose — a set of coordinates of thirty-ish points. I record a person for some duration (10 seconds to 1 minute). I want to have the embedding of the ...
2
votes
1
answer
445
views
How embeddings learned from one model can be used in another?
In the website the following explanation is provided about Embedding layer:
The Embedding layer is initialized with random weights and will learn
an embedding for all of the words in the training ...
0
votes
0
answers
58
views
How to fix the embedding gauge in a BERT-like model?
I have a pre-trained BERT model from Huggingface, which I tune to categorize short texts (like tweets or slightly longer) into several thousand categories using triplet loss.
As I understand, if I ...
0
votes
0
answers
39
views
Can Graph Neural network leverage only the topological structure?
Graph Neural Networks (GNNs) are a powerful tool that allow learning on graphs by leveraging both the topological structure and the feature information for each node.
For the particular problem I am ...
2
votes
2
answers
952
views
What is the difference between representation and embedding?
As I searched about this two terms, I found they are somehow like each other, both try to create a vector from raw data as I understood. But, what is the difference of this two term?
0
votes
1
answer
150
views
What is the distribution of autoencoder embeddings?
Is there any result on the distribution of autoencoder embeddings?
For example, the following image (taken from this article) visualizes the latent space with t-SNE. As you can see, images from the ...
1
vote
2
answers
2k
views
How does GPT use the same embedding matrix for both input and output?
My understanding is that GPT uses the same embedding matrix for both inputs and output: Let $V$ be the vocab size, $D$ the number of embedding dimensions, and $E$ be a $V \times D$ embedding matrix:
...
1
vote
1
answer
377
views
What is a "continuous vector"?
I have seen the concept of a "continuous vector" described in the context of embeddings. For instance, this answer to a question on embeddings in the context of deep learning. I obviously ...
0
votes
0
answers
21
views
Prototypical Network - Should I train my backbone or a separate embedder?
When I read the prototypical paper Prototypical Networks for Few-shot Learning, I understand in Eq. 1 that I should train $f_\phi$, which takes as input $x_i$, which is already an embedding of an ...
7
votes
2
answers
1k
views
Why are embeddings added, not concatenated?
Let's consider the following example from BERT
I cannot understand why "the input embeddings are the sum of the token embeddings, the segmentation embeddings, and the position embeddings". ...
0
votes
1
answer
38
views
Can I use Sentence-Bert to embed event triples?
I extracted event triples from sentences using OpenIE. Can I concatenate the components in the event triple to make it a sentence and use Sentence-Bert to embed the event?
It seems no one has done ...
0
votes
0
answers
41
views
Could I cluster the audio clips in order to improve the speed of their classification?
I have a neural network which is very resource intensive and is used to classify audio clips. The classification is done in batches, where I record for a set period of time and then go through and ...
1
vote
1
answer
483
views
Is "node embedding" in GNN analogous to "hidden layer" of FFN?
So in Graph Neural Network (GNN) we have node embeddings which is a feature vector that describes the node, is it analogous to hidden layer of Artificial neural network such as feed-forward neural ...
0
votes
1
answer
65
views
Sensible integer embedding/encoding for distinguishing elements of a set?
I am trying to train a model that takes in a set of feature vectors (which comes with an ID to uniquely identify elements of the set) and outputs a target for each element in the set (in a permutation-...
1
vote
1
answer
962
views
Sequence Embedding using embedding layer: how does the network architecture influence it?
I want to obtain a dense vector representation of protein sequences so that I can meaningfully represent them in an embedding space. We can consider them as sequences of letters, in particular there ...
0
votes
2
answers
127
views
How do multimodal models establish connections between different modes?
I am specifically interested in data2vec, Meta's new model that can convert image, text, and sound data into a unified neural network representation. To my understanding, they did this through self-...
1
vote
1
answer
223
views
Perform clustering on high dimensional data
Recently I trained a BYOL model on a set of images to learn an embedding space where similar vectors are close by. The performance was fantastic when I performed approximate K-nearest neighbours ...
3
votes
1
answer
138
views
What are knowledge graph embeddings?
What are knowledge graph embeddings? How are they useful? Are there any extensive reviews on the subject to know all the details? Note that I am asking this question just to give a quick overview of ...
2
votes
0
answers
28
views
Is there any way to force one input have more effect on model?
Now I am working on building a deep learning model for a regression problem. I used 50 inputs and try to add one new categorical input. The problem is that this one input is much more important than ...
0
votes
1
answer
67
views
Best way to resize 3d to 2d matrix
I have a (5, 128, 768) matrix, that is, I have 5 embedding spaces of shape (128, 768). Since they all keep a relation, and for ...
1
vote
0
answers
31
views
How do the scale of an embedding affects a downstream task?
I am currently training a neural network in a self-supervised fashion, using Contrastive Loss and I want to use that network then to fine-tune it in a classification task with a small fraction of the ...
1
vote
0
answers
24
views
What is the reason behind using node embeddings?
I was reading Chapter 3 from the following book (here) on graph representation learning. The chapter is about node embeddings.
Question: What is the point of using node embeddings?
Do we use them:
to ...
1
vote
0
answers
24
views
Is graph embedding linear in its maintaining of graph geometry?
It is claimed that the main goal of graph embedding methods is to pack every node's properties into a vector with a smaller dimension, so node similarity in the original complex irregular spaces can ...
7
votes
3
answers
11k
views
How to determine the embedding size?
When we are training a neural network, we are going to determine the embedding size to convert the categorical (in NLP, for instance) or continuous (in computer vision or voice) information to hidden ...