Neural Collaborative Filtering in 2D: Watch Embeddings Learn Live

Training

Hidden units 4

Learning rate 0.50

Explore a viewer

—

Live Metrics

Epoch

Accuracy

—

BCE loss

—

Top score

—

How it works

Classic matrix factorization predicts a rating as a plain dot product p_u·q_i of a user embedding and an item embedding — a linear model. Neural Collaborative Filtering (He et al., 2017) replaces that dot product with a small neural network that can learn a non-linear interaction function instead:

x = [p_u ; q_i]                (concat, 4-dim in this 2D build)
z1 = W1·x + b1 ;  h = ReLU(z1)   (hidden layer)
z2 = W2·h + b2 ;  ŷ = σ(z2)      (predicted score, 0-1)
loss = −Σ [y·log ŷ + (1−y)·log(1−ŷ)]   (binary cross-entropy)

Every training step runs full-batch gradient descent: it backpropagates the loss through the output, the hidden layer, and all the way into the embeddings themselves — so p_u and q_i are learned jointly with the network weights, not fixed in advance. That is why the dots in the scatter plot visibly drift during training: the model is reshaping the 2D latent space so a viewer ends up close, in this learned geometry, to the movies their network activations predict they'll like.

Hidden units — width of the interaction layer; more units can fit sharper non-linear boundaries between genres, at the cost of needing more data.
Learning rate — step size of each gradient-descent update; watch the loss sparkline get noisier as you push it higher.
Explore a viewer — draws a live line from that viewer to every movie in the scatter plot, brightness set by the model's current predicted score ŷ.
Drag / scroll on the scatter plot — pan and zoom the embedding space; the node-link and sparkline panels stay fixed as reference.

This toy catalogue is small and dense enough to train on every pair each epoch; production recommenders (YouTube's deep ranking model, for example) face millions of items and instead train on sampled negatives, but the underlying embed-then-interact math is the same.

Viewers Movies Hidden units

drag to pan · scroll to zoom