Architectures / Recommendation

🗼 Two-Tower

User+Item dual encoder for retrieval — embeddings → MLP per side → dot product score

Layers

Parameters

70.43M

Input

Output

1 × 64

Verifier

Clean

Every number on this page is computed from the graph by the same functions the app runs, not written by hand.

Open Two-Tower on the canvas Free, no account needed

When to pick it

Pick for retrieval at scale (billions of items) where item embeddings can be precomputed and indexed. Not suitable for re-ranking — no cross-features.

Structure

12 layers. Output shapes are propagated from the input shape, batch dimension excluded.

	Layer	Type	Parameters	Output shape
1	User Input	Input	shape=[1]	1
2	User Embed	Embedding	vocabSize=100000	1 × 64
3	User FC 1	Linear	outFeatures=128, inFeatures=64	1 × 128
4	User ReLU	ReLU		1 × 128
5	User Tower Out	Linear	outFeatures=64, inFeatures=128	1 × 64
6	Item Input	Input	shape=[1]	1
7	Item Embed	Embedding	vocabSize=1000000	1 × 64
8	Item FC 1	Linear	outFeatures=128, inFeatures=64	1 × 128
9	Item ReLU	ReLU		1 × 128
10	Item Tower Out	Linear	outFeatures=64, inFeatures=128	1 × 64
11	Dot Score	MatMul		1 × 64
12	Score	Output		1 × 64

What the verifier says

The same 41 structural checks that run on every edit in the app, on this graph.

info9 layers with no BatchNorm, LayerNorm, or GroupNorm. Without normalization, activations can explode or vanish across layers, causing slow or unstable training. Fix: Add BatchNorm after Conv2d (CV tasks), LayerNorm after attention/FFN (NLP/LLM), or GroupNorm for small batch sizes.
deep-no-norm

The PyTorch it exports

Generated from the graph above. First 46 lines; the app exports the whole file, plus the training loop, the data contract and a deploy bundle.

# Architecture designed with Neurarch: https://neurarch.com
# PyTorch: compatible with Python 3.8+ and torch>=1.12
# Colab: pip install torch torchvision  (usually pre-installed)
#
# WARNING: 1 layer(s) below are not yet supported by the PyTorch
# exporter and pass their input through UNCHANGED in forward():
#   - Dot Score (matmul)

import torch
import torch.nn as nn
import torch.nn.functional as F
from typing import Tuple

class Two_Tower(nn.Module):
    def __init__(self):
        super().__init__()

        self.embedding_1 = nn.Embedding(100000, 64)
        self.linear_1 = nn.Linear(64, 128)
        self.linear_2 = nn.Linear(128, 64)
        self.embedding_2 = nn.Embedding(1000000, 64)
        self.linear_3 = nn.Linear(64, 128)
        self.linear_4 = nn.Linear(128, 64)

    def forward(self, src, tgt=None):
        # User Input shape: [1]
        # Item Input shape: [1]
        embedding_er_emb = self.embedding_1(src)
        linear_er_fc1 = self.linear_1(embedding_er_emb)
        relu_r_relu = F.relu(linear_er_fc1)
        linear_er_fc2 = self.linear_2(relu_r_relu)
        embedding_em_emb = self.embedding_2(tgt)
        linear_em_fc1 = self.linear_3(embedding_em_emb)
        relu_m_relu = F.relu(linear_em_fc1)
        linear_em_fc2 = self.linear_4(relu_m_relu)
        # TODO: layer 'Dot Score' (matmul) is not yet supported by the exporter; passing through unchanged
        # Output
        return linear_er_fc2


if __name__ == '__main__':
    model = Two_Tower()
    model.eval()

    src = torch.randint(0, 1, (1))  # (batch, src_seq_len)
    tgt = torch.randint(0, 1, (1))  # (batch, tgt_seq_len)

For agents

This architecture is machine-readable end to end. An agent can list the set, fetch this graph, edit it, and have the edit verified before any GPU time is spent.

Markdown twin Index JSON This graph as JSON MCP server POST /api/v1/check

Also in Recommendation

Meta's Deep Learning Recommendation Model — bottom MLP for dense, embedding for sparse, feature interaction, top MLP

14 layers · 32.35M

🤝 Neural Collaborative Filtering

He et al

16 layers · 105.61M

🕸 GraphSAGE Recommender

Inductive node embeddings via neighbor sampling + aggregation — for graph-based recommenders

10 layers · 263.0K