Refactored, 2x-longer survey of Transformer architecture improvements since 2020
Reference notation table for attention, heads, and positional encoding math
Covers vanilla encoder-decoder plus BERT and GPT variants
Key quotes
“Version 2.0 is a superset of the old version, about twice the length.”
“Later simplified Transformer was shown to achieve great performance in language modeling tasks, like in encoder-only BERT or decoder-only GPT .”
Transcript
Many new Transformer architecture improvements have been proposed since my last post on “The Transformer Family” about three years ago. Here I did a big refactoring and enrichment of that 2020 post — restructure the hierarchy of sections and improve many sections with more recent papers. Version 2.0 is a superset of the old version, about twice the length. Notations Symbol Meaning $d$ The model size / hidden state dimension / positional encoding size. $h$ The number of heads in multi-head attention layer. $L$ The segment length of input sequence. $N$ The total number of attention layers in the model; not considering MoE. $\mathbf{X} \in \mathbb{R}^{L \times d}$ The input sequence where each element has been mapped into an embedding vector of shape $d$, same as the model size. $\mathbf{W}^k \in \mathbb{R}^{d \times d_k}$ The key weight matrix. $\mathbf{W}^q \in \mathbb{R}^{d \times d_k}$ The query weight matrix. $\mathbf{W}^v \in \mathbb{R}^{d \times d_v}$ The value weight matrix. Often we have $d_k = d_v = d$. $\mathbf{W}^k_i, \mathbf{W}^q_i \in \mathbb{R}^{d \times d_k/h}; \mathbf{W}^v_i \in \mathbb{R}^{d \times d_v/h}$ The weight matrices per head. $\mathbf{W}^o \in \mathbb{R}^{d_v \times d}$ The output weight matrix. $\mathbf{Q} = \mathbf{X}\mathbf{W}^q \in \mathbb{R}^{L \times d_k}$ The query embedding inputs. $\mathbf{K} = \mathbf{X}\mathbf{W}^k \in \mathbb{R}^{L \times d_k}$ The key embedding inputs. $\mathbf{V} = \mathbf{X}\mathbf{W}^v \in \mathbb{R}^{L \times d_v}$ The value embedding inputs. $\mathbf{q}_i, \mathbf{k}_i \in \mathbb{R}^{d_k}, \mathbf{v}_i \in \mathbb{R}^{d_v}$ Row vectors in query, key, value matrices, $\mathbf{Q}$, $\mathbf{K}$ and $\mathbf{V}$. $S_i$ A collection of key positions for the $i$-th query $\mathbf{q}_i$ to attend to. $\mathbf{A} \in \mathbb{R}^{L \times L}$ The self-attention matrix between a input sequence of lenght $L$ and itself. $\mathbf{A} = \text{softmax}(\mathbf{Q}\mathbf{K}^\top / \sqrt{d_k})$. $a_{ij} \in \mathbf{A}$ The scalar attention score between query $\mathbf{q}_i$ and key $\mathbf{k}_j$. $\mathbf{P} \in \mathbb{R}^{L \times d}$ position encoding matrix, where the $i$-th row $\mathbf{p}_i$ is the positional encoding for input $\mathbf{x}_i$. Transformer Basics The Transformer (which will be referred to as “vanilla Transformer” to distinguish it from other enhanced versions; Vaswani, et al., 2017 ) model has an encoder-decoder architecture, as commonly used in many NMT models. Later simplified Transformer was shown to achieve great performance in language modeling tasks, like in encoder-only BERT or decoder-only GPT .
