Multi-head attention

As explained in Optimization Algorithms: AI techniques for design, planning, and control problems

Multi-head self-attention computes several attention operations in parallel so a sequence representation can capture different relationships among its elements.

Multi-head attention runs several attention operations in parallel. Each head can focus on different input parts, helping representations capture multiple relationships and patterns. section 11.3.2

In graph attention networks, each head can attend to neighboring nodes differently. Attention scores are commonly normalized with softmax; head outputs are then typically averaged before a final nonlinearity produces prediction probabilities. section 11.3.2

Three heads attending from node 5

With H = 3 heads, node 5 assigns attention coefficients such as α52, α54, and α55. Each head aggregates features differently, and the resulting embeddings are averaged into node 5’s final representation. section 11.3.2

Figure 11.10 Multi-head attention with H = 3 heads by node 5. α₅₂, α₅₄, and α₅₅ are the attention coefficients between the nodes. The aggregated features from each head are averaged to obtain the final embedding of the node.

Inspect the three-head graph example and its averaged node embedding. section 11.3.2

How Optimization Algorithms: AI techniques for design, planning, and control problems covers it

How deep it goes

Explains multiple heads, neighborhood attention, softmax normalization, averaging, and final nonlinearities without implementation details.

Examples

Illustrates three attention heads aggregating features for node 5 before averaging their embeddings.

What it assumes

Assumes attention scores, neighborhoods, softmax normalization, and graph or sequence representations.

What you can do after

Evaluate how multiple attention heads combine distinct neighborhood perspectives into a prediction-ready representation.

How it connects

Connects attention coefficients, softmax, graph attention networks, and Transformer models.

liveBookmanning.com

Read Optimization Algorithms: AI techniques for design, planning, and control problems on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionMulti-head attention computes multiple attention representations in parallel and combines them, potentially using distinct query and source sequences.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)An attention mechanism that computes attention through multiple separate query, key, and value subspaces to capture different relationships simultaneously.
• 

  liveBookmanning.com
  Transformers in ActionMultihead attention is an attention mechanism that computes multiple attention patterns in parallel so a model can represent different relationships among sequence positions.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA self-attention variant that splits representations into multiple attention heads to capture different relationships in parallel.
• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsAn attention mechanism that uses multiple attention heads to attend to different contexts or aspects of the input in parallel.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionAn attention variant that runs several attention computations in parallel with different parameters to learn different relationships.
• 

  liveBookmanning.com
  Graph Neural Networks in ActionAn attention technique that computes multiple attention operations in parallel and combines their outputs.
• 

  liveBookmanning.com
  Build a Large Language Model (From Scratch)An attention technique that computes several independent attention heads in parallel and combines their outputs to capture different relationships in the same sequence.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionMultiHeadAttention is a Keras layer that computes attention through multiple parallel attention heads and combines their outputs.
• 

  liveBookmanning.com
  Time Series Forecasting Using Foundation ModelsAn attention mechanism with multiple parallel attention heads that combines information from different representation subspaces.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthMultihead attention runs multiple attention mechanisms in parallel and combines their output representations.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionAn attention mechanism that runs several attention heads in parallel, each learning different projections and relationships.
• 

  liveBookmanning.com
  The AI Pocket BookA transformer attention mechanism that splits representations into multiple heads to attend to different relationships in parallel.

Compare how 14 books explain multi-head attention →

Related concepts

• graph attention networkused by · A graph attention network is a graph neural network that uses attention weights to aggregate information from neighboring nodes, allowing their contributions to differ.
• grouped-query attentionequivalent to · Grouped-query attention partitions query heads into groups whose members share key and value projections, reducing attention computation and memory use.
• attentionkind of · Attention is a neural-network mechanism that computes input-dependent weights to combine information according to its relevance to a computation.
• attention headhas part · An attention head is an independently parameterized attention computation that evaluates relationships among input elements and combines information from them into a contextualized representation.
• transformer architectureused by · A transformer architecture is a neural-network architecture that processes sequences or other structured inputs using attention mechanisms and related transformations.
• encoderpart of · An encoder is a component that transforms input data into an encoded representation for subsequent processing, reconstruction, comparison, or transmission.

This explainer was generated by Manning's knowledge graph from the text of Optimization Algorithms: AI techniques for design, planning, and control problems. The section links point to the parts of the book it draws on.