N Neurarch Architectures Models Checks Data Docs Open the app

Comparisons / Wide & Deep vs Neural Collaborative Filtering

Wide & Deep vs Neural Collaborative Filtering

The memorisation-plus-generalisation recommender against a purely neural one.

Neural Collaborative Filtering has 32M more parameters than Wide & Deep: 2 layers added, 3 removed, 5 changed.

Baseline

Wide & Deep

Layers
10
Parameters
3.7M
Input
10000
Output
1
Forward-passes
yes
Est. train cost
$0.043
Compared

Neural Collaborative Filtering

Layers
9
Parameters
35M
Input
1
Output
1 × 1
Forward-passes
yes
Est. train cost
$0.053

The deltas

Every number is Neural Collaborative Filtering relative to Wide & Deep.

Parameters
+32M (9.6× the size)
Layers
-1
Added
2
Removed
3
Changed
5
Unchanged
5

Which GPUs each one fits

Each side is measured at its own declared input (10000 against 1). Both columns are right about their own model; the difference between them is not a fact about the designs.

GPUWide & DeepNeural Collaborative Filtering
T4 16GBfitsfits
A100 40GBfitsfits
H100 80GBfitsfits

Layer by layer

Aligned in topological order. 5 of 15 rows are the same layer with the same parameters.

Hide all 15 rows
Wide & DeepNeural Collaborative Filtering
LayerParamsOutputLayerParamsOutput
1changed
shape
Wide Input (cross feats)
Input
10000User ID
Input
1
2changed
shape
Deep Input (sparse cat)
Input
50Item ID
Input
1
3removedWide Linear
Linear
10K1
4sameEmbeddings
Embedding
3.2M50 × 32User Embedding
Embedding
3.2M1 × 32
5removedFlatten
Flatten
1600
6addedItem Embedding
Embedding
32M1 × 32
7addedConcat [u; i]
Concatenate
1 × 64
8changed
inFeatures, outFeatures
Deep FC 1
Linear
410K256MLP 1
Linear
4.2K1 × 64
9sameReLU 1
Relu
256ReLU 1
Relu
1 × 64
10changed
inFeatures, outFeatures
Deep FC 2
Linear
33K128MLP 2
Linear
2.1K1 × 32
11sameReLU 2
Relu
128ReLU 2
Relu
1 × 32
12changed
inFeatures
Deep Out
Linear
1291Score Head
Linear
331 × 1
13removedWide + Deep
Add
1
14sameSigmoid CTR
Sigmoid
1Sigmoid
Sigmoid
1 × 1
15sameP(click)
Output
1P(click)
Output
1 × 1

What this is not

Take it further

Open either graph in the editor, change it, and check it again: Wide & Deep · Neural Collaborative Filtering

Compare any two models of your own, including anything on Hugging Face: the comparison tool.

Machine-readable: this page as markdown · the pair index · POST https://www.neurarch.com/api/v1/plan for a graph of your own.

Related comparisons

Neural Collaborative Filtering vs Neural Collaborative Filtering
Neural collaborative filtering against its generalised-matrix-factorisation hybrid.
Two-Tower vs Neural Collaborative Filtering
Retrieval by dot product against a learned interaction.
DLRM vs Wide & Deep
Two production ranking models with different interaction layers.