Reading Time: 24 minutes

[ad_1]


This article is one of two Distill publications about graph neural networks.
Take a look at
A Gentle Introduction to Graph Neural Networks

for a companion view on many things graph and neural network related.

Many systems and interactions – social networks, molecules, organizations, citations, physical models, transactions – can be represented quite naturally as graphs.
How can we reason about and make predictions within these systems?

One idea is to look at tools that have worked well in other domains: neural networks have shown immense predictive power in a variety of learning tasks.
However, neural networks have been traditionally used to operate on fixed-size and/or regular-structured inputs (such as sentences, images and video).
This makes them unable to elegantly process graph-structured data.

Neural networks generally operate on fixed-size input vectors. How do we input a graph to a neural network?

Graph neural networks (GNNs) are a family of neural networks that can operate naturally on graph-structured data.
By extracting and utilizing features from the underlying graph,
GNNs can make more informed predictions about entities in these interactions,
as compared to models that consider individual entities in isolation.

GNNs are not the only tools available to model graph-structured data:
graph kernels
and random-walk methods
were some of the most popular ones.
Today, however, GNNs have largely replaced these techniques
because of their inherent flexibility to model the underlying systems
better.

In this article, we will illustrate
the challenges of computing over graphs,
describe the origin and design of graph neural networks,
and explore the most popular GNN variants in recent times.
Particularly, we will see that many of these variants
are composed of similar building blocks.

First, let’s discuss some of the complications that graphs come with.

The Challenges of Computation on Graphs

Lack of Consistent Structure

Graphs are extremely flexible mathematical models; but this means they lack consistent structure across instances.
Consider the task of predicting whether a given chemical molecule is toxic  :

The molecular structure of non-toxic 1,2,6-trigalloyl-glucose.
The molecular structure of toxic caramboxin.
Left: A non-toxic 1,2,6-trigalloyl-glucose molecule.
Right: A toxic caramboxin molecule.

Looking at a few examples, the following issues quickly become apparent:

  • Molecules may have different numbers of atoms.
  • The atoms in a molecule may be of different types.
  • Each of these atoms may have different number of connections.
  • These connections can have different strengths.

Representing graphs in a format that can be computed over is non-trivial,
and the final representation chosen often depends significantly on the actual problem.

Node-Order Equivariance

Extending the point above: graphs often have no inherent ordering present amongst the nodes.
Compare this to images, where every pixel is uniquely determined by its absolute position within the image!

Representing the graph as one vector requires us to fix an order on the nodes. But what do we do when the nodes have no inherent order?
Representing the graph as one vector requires us to fix an order on the nodes.
But what do we do when the nodes have no inherent order?
Above:
The same graph labelled in two different ways. The alphabets indicate the ordering of the nodes.

As a result, we would like our algorithms to be node-order equivariant:
they should not depend on the ordering of the nodes of the graph.
If we permute the nodes in some way, the resulting representations of
the nodes as computed by our algorithms should also be permuted in the same way.

Scalability

Graphs can be really large! Think about social networks like Facebook and Twitter, which have over a billion users.
Operating on data this large is not easy.

Luckily, most naturally occuring graphs are ‘sparse’:
they tend to have their number of edges linear in their number of vertices.
We will see that this allows the use of clever methods
to efficiently compute representations of nodes within the graph.
Further, the methods that we look at here will have significantly fewer parameters
in comparison to the size of the graphs they operate on.

Problem Setting and Notation

There are many useful problems that can be formulated over graphs:

  • Node Classification: Classifying individual nodes.
  • Graph Classification: Classifying entire graphs.
  • Node Clustering: Grouping together similar nodes based on connectivity.
  • Link Prediction: Predicting missing links.
  • Influence Maximization: Identifying influential nodes.
Examples of problems that can be defined over graphs.
Examples of problems that can be defined over graphs.
This list is not exhaustive!

A common precursor in solving many of these problems is node representation learning:
learning to map individual nodes to fixed-size real-valued vectors (called ‘representations’ or ‘embeddings’).

In Learning GNN Parameters, we will see how the learnt embeddings can be used for these tasks.

Different GNN variants are distinguished by the way these representations are computed.
Generally, however, GNNs compute node representations in an iterative process.
We will use the notation

hv(k)h_v^{(k)}

vv

after the

kthk^{text{th}}

We will define a graph

GG

as a set of nodes,

VV

, with a set of edges

EE

connecting them.
Nodes can have individual features as part of the input: we will denote by

xvx_v

vVv in V

.
For example, the ‘node features’ for a pixel in a color image
would be the red, green and blue channel (RGB) values at that pixel.

For ease of exposition, we will assume

GG

is undirected, and all nodes are of the same type.
These kinds of graphs are called ‘homogeneous’.
Many of the same ideas we will see here
apply to other kinds of graphs:
we will discuss this later in Different Kinds of Graphs.

Sometimes we will need to denote a graph property by a matrix

MM

,
where each row

MvM_v

vv

.

Extending Convolutions to Graphs

Convolutional Neural Networks have been seen to be quite powerful in extracting features from images.
However, images themselves can be seen as graphs with a very regular grid-like structure,
where the individual pixels are nodes, and the RGB channel values at each pixel as the node features.

A natural idea, then, is to consider generalizing convolutions to arbitrary graphs. Recall, however, the challenges
listed out in the previous section: in particular, ordinary convolutions are not node-order invariant, because
they depend on the absolute positions of pixels.
It is initially unclear as how to generalize convolutions over grids to convolutions over general graphs,
where the neighbourhood structure differs from node to node.

The curious reader may wonder if performing some sort of padding and ordering
could be done to ensure the consistency of neighbourhood structure across nodes.
This has been attempted with some success ,
but the techniques we will look at here are more general and powerful.

Convolutions in CNNs are inherently localized.
Neighbours participating in the convolution at the center pixel are highlighted in gray.
GNNs can perform localized convolutions mimicking CNNs.
Hover over a node to see its immediate neighbourhood highlighted on the left.
The structure of this neighbourhood changes from node to node.

We begin by introducing the idea of constructing polynomial filters over node neighbourhoods,
much like how CNNs compute localized filters over neighbouring pixels.
Then, we will see how more recent approaches extend on this idea with more powerful mechanisms.
Finally, we will discuss alternative methods
that can use ‘global’ graph-level information for computing node representations.

Polynomial Filters on Graphs

The Graph Laplacian

Given a graph

GG

, let us fix an arbitrary ordering of the

nn

nodes of

GG

.
We denote the

010-1

adjacency matrix of

GG

by

AA

, we can construct the diagonal degree matrix

DD

of

GG

as:

Dv=uAvu.
D_v = sum_u A_{vu}.

The degree of node

vv

is the number of edges incident at

vv

.

where

AvuA_{vu}

vv

and the column corresponding to

uu


in the matrix

AA

. We will use this notation throughout this section.

Then, the graph Laplacian

LL

is the square

n×nn times n

matrix defined as:

L=DA.
L = D – A.

laplacian |
The Laplacian

LL

for an undirected graph

GG

, with the row corresponding to node

Ctextsf{C}

highlighted.
Zeros in

LL

are not displayed above.
The Laplacian

LL

depends only on the structure of the graph

GG

, not on any node features.

The graph Laplacian gets its name from being the discrete analog of the
Laplacian operator
from calculus.

Although it encodes precisely the same information as the adjacency matrix

AA



In the sense that given either of the matrices

AA

or

LL

, you can construct the other.
,
the graph Laplacian has many interesting properties of its own.

The graph Laplacian shows up in many mathematical problems involving graphs:
random walks,
spectral clustering,
and
diffusion, to name a few.

We will see some of these properties
in a later section,
but will instead point readers to
this tutorial
for greater insight into the graph Laplacian.

Polynomials of the Laplacian

Now that we have understood what the graph Laplacian is,
we can build polynomials of the form:

pw(L)=w0In+w1L+w2L2++wdLd=i=0dwiLi.
p_w(L) = w_0 I_n + w_1 L + w_2 L^2 + ldots + w_d L^d = sum_{i = 0}^d w_i L^i.

w=[w0,,wd]w = [w_0, ldots, w_d]

ww

,

pw(L)p_w(L)

n×nn times n

matrix, just like

LL

.

These polynomials can be thought of as the equivalent of ‘filters’ in CNNs,
and the coefficients

ww

as the weights of the ‘filters’.

For ease of exposition, we will focus on the case where nodes have one-dimensional features:
each of the

xvx_v

vVv in V

is just a real number.
The same ideas hold when each of the

xvx_v

Using the previously chosen ordering of the nodes,
we can stack all of the node features

xvx_v

xRnx in mathbb{R}^n

Fixing a node order and collecting all node features into a single vector.
Fixing a node order (indicated by the alphabets) and collecting all node features into a single vector

xx

.

Once we have constructed the feature vector

xx

,
we can define its convolution with a polynomial filter

pwp_w

x=pw(L) x
x’ = p_w(L) x

ww

affect the convolution,
let us begin by considering the ‘simplest’ polynomial:
when

w0=1w_0 = 1

00

.
In this case,

xx’

xx

:

x=pw(L) x=i=0dwiLix=w0Inx=x.
x’ = p_w(L) x = sum_{i = 0}^d w_i L^ix = w_0 I_n x = x.

w1=1w_1 = 1

00

.
Then,

xx’

LxLx

, and so:

xv=(Lx)v=Lvx=uGLvuxu=uG(DvuAvu)xu=Dv xvuN(v)xu
begin{aligned}
x’_v = (Lx)_v &= L_v x \
&= sum_{u in G} L_{vu} x_u \
&= sum_{u in G} (D_{vu} – A_{vu}) x_u \
&= D_v x_v – sum_{u in mathcal{N}(v)} x_u
end{aligned}

vv

are combined
with the features of its immediate neighbours

uN(v)u in mathcal{N}(v)

.

For readers familiar with
Laplacian filtering of images,
this is the exact same idea. When

xx

is an image,

x=Lxx’ = Lx

xx

.

At this point, a natural question to ask is:
How does the degree

dd

of the polynomial influence the behaviour of the convolution?
Indeed, it is not too hard to show that:
This is Lemma 5.2 from .

distG(v,u)>iLvui=0.
text{dist}_G(v, u) > i quad Longrightarrow quad L_{vu}^i = 0.

This implies, when we convolve

xx

with

pw(L)p_w(L)

dd

to get

xx’

xv=(pw(L)x)v=(pw(L))vx=i=0dwiLvix=i=0dwiuGLvuixu=i=0dwiuGdistG(v,u)iLvuixu.
begin{aligned}
x’_v = (p_w(L)x)_v &= (p_w(L))_v x \
&= sum_{i = 0}^d w_i L_v^i x \
&= sum_{i = 0}^d w_i sum_{u in G} L_{vu}^i x_u \
&= sum_{i = 0}^d w_i sum_{u in G atop text{dist}_G(v, u) leq i} L_{vu}^i x_u.
end{aligned}

Effectively, the convolution at node

vv

occurs only with nodes

uu

which are not more than

dd

hops away.
Thus, these polynomial filters are localized. The degree of the localization is governed completely by

dd

.

To help you understand these ‘polynomial-based’ convolutions better, we have created the visualization below.
Vary the polynomial coefficients and the input grid

xx

to see how the result

xx’

xx

to get
the resulting pixel in

xx’

pw(L)p_w(L)

Hover over a pixel in the input grid (left, representing

xx

)
to highlight it and see the equivalent convolutional kernel
for that pixel under the arrow.
The result

xx’

Click on the input grid to toggle pixel values between

00

(white) and

11

(blue).
To randomize the input grid, press ‘Randomize Grid’. To reset all pixels to

00

, press ‘Reset Grid’.
Use the sliders at the bottom to change the coefficients

ww

.
To reset all coefficients

ww

to

00

, press ‘Reset Coefficients.’

ChebNet


ChebNet refines this idea of polynomial filters by looking at polynomial filters of the form:

pw(L)=i=1dwiTi(L~)
p_w(L) = sum_{i = 1}^d w_i T_i(tilde{L})

TiT_i

ii


Chebyshev polynomial of the first kind and

L~tilde{L}

LL

:

We discuss the eigenvalues of the Laplacian

LL

in more detail in a later section.


L~=2Lλmax(L)In.
tilde{L} = frac{2L}{lambda_{max}(L)} – I_n.

What is the motivation behind these choices?

  • LL

    is actually positive semi-definite: all of the eigenvalues of

    LL

    are not lesser than

    00

    .
    If

    λmax(L)>1lambda_{max}(L) > 1

    LL

    rapidly increase in size.

    L~tilde{L}

    LL

    , with eigenvalues guaranteed to be in the range

    [1,1][-1, 1]

    .
    This prevents the entries of powers of

    L~tilde{L}

    LL

    is selected, but allow larger values when the normalized Laplacian

    L~tilde{L}

    xx’

  • The Chebyshev polynomials have certain interesting properties that make interpolation more numerically stable.
    We won’t talk about this in more depth here,
    but will advise interested readers to take a look at as a definitive resource.

Polynomial Filters are Node-Order Equivariant

The polynomial filters we considered here are actually independent of the ordering of the nodes.
This is particularly easy to see when the degree of the polynomial

pwp_w

11

:
where each node’s feature is aggregated with the sum of its neighbour’s features.
Clearly, this sum does not depend on the order of the neighbours.
A similar proof follows for higher degree polynomials:
the entries in the powers of

LL

are equivariant to the ordering of the nodes.

Details for the Interested Reader

As above, let’s assume an arbitrary node-order over the

nn

nodes of our graph.
Any other node-order can be thought of as a permutation of this original node-order.
We can represent any permutation by a
permutation matrix

PP

.

PP

will always be an orthogonal

010-1

matrix:

PPT=PTP=In.
PP^T = P^TP = I_n.

ff

node-order equivariant iff for all permutations

PP

:

f(Px)=Pf(x).
f(Px) = P f(x).

When switching to the new node-order using the permutation

PP

,
the quantities below transform in the following way:

xPxLPLPTLiPLiPT
begin{aligned}
x &to Px \
L &to PLP^T \
L^i &to PL^iP^T
end{aligned}

f(Px)=i=0dwi(PLiPT)(Px)=Pi=0dwiLix=Pf(x).
begin{aligned}
f(Px) & = sum_{i = 0}^d w_i (PL^iP^T) (Px) \
& = P sum_{i = 0}^d w_i L^i x’ \
& = P f(x).
end{aligned}

Embedding Computation

We now describe how we can build a graph neural network
by stacking ChebNet (or any polynomial filter) layers
one after the other with non-linearities,
much like a standard CNN.
In particular, if we have

KK

different polynomial filter layers,
the

kthk^{text{th}}

w(k)w^{(k)}

Note that these networks
reuse the same filter weights across different nodes,
exactly mimicking weight-sharing in Convolutional Neural Networks (CNNs)
which reuse weights for convolutional filters across a grid.

Modern Graph Neural Networks

ChebNet was a breakthrough in learning localized filters over graphs,
and it motivated many to think of graph convolutions from a different perspective.


We return back to the result of convolving

xx

by the polynomial kernel

pw(L)=Lp_w(L) = L

vv

:

(Lx)v=Lvx=uGLvuxu=uG(DvuAvu)xu=Dv xvuN(v)xu
begin{aligned}
(Lx)_v &= L_v x \
&= sum_{u in G} L_{vu} x_u \
&= sum_{u in G} (D_{vu} – A_{vu}) x_u \
&= D_v x_v – sum_{u in mathcal{N}(v)} x_u
end{aligned}

As we noted before, this is a

11

-hop localized convolution.
But more importantly, we can think of this convolution as arising of two steps:

  • Aggregating over immediate neighbour features
    xux_u

  • Combining with the node’s own feature
    xvx_v

Key Idea:
What if we consider different kinds of ‘aggregation’ and ‘combination’ steps,
beyond what are possible using polynomial filters?

By ensuring that the aggregation is node-order equivariant,
the overall convolution becomes node-order equivariant.

These convolutions can be thought of as ‘message-passing’ between adjacent nodes:
after each step, every node receives some ‘information’ from its neighbours.

By iteratively repeating the

11

-hop localized convolutions

KK

times (i.e., repeatedly ‘passing messages’),
the receptive field of the convolution effectively includes all nodes upto

KK

hops away.

Embedding Computation

Message-passing forms the backbone of many GNN architectures today.
We describe the most popular ones in depth below:

  • Graph Convolutional Networks (GCN)
  • Graph Attention Networks (GAT)
  • Graph Sample and Aggregate (GraphSAGE)
  • Graph Isomorphism Network (GIN)

Thoughts

An interesting point is to assess different aggregation functions: are some better and others worse?
demonstrates that aggregation functions indeed can be compared on how well
they can uniquely preserve node neighbourhood features;
we recommend the interested reader take a look at the detailed theoretical analysis there.

Here, we’ve talk about GNNs where the computation only occurs at the nodes.
More recent GNN models
such as Message-Passing Neural Networks
and Graph Networks
perform computation over the edges as well;
they compute edge embeddings together with node embeddings.
This is an even more general framework –
but the same ‘message passing’ ideas from this section apply.

Interactive Graph Neural Networks

Below is an interactive visualization of these GNN models on small graphs.
For clarity, the node features are just real numbers here, shown inside the squares next to each node,
but the same equations hold when the node features are vectors.

Choose a GNN model using the tabs at the top. Click on a node to see the update equation at that node for the next iteration.
Use the sliders on the left to change the weights for the current iteration, and watch how the update equation changes.

In practice, each iteration above is generally thought of as a single ‘neural network layer’.
This ideology is followed by many popular Graph Neural Network libraries,

For example: PyTorch Geometric
and StellarGraph.

allowing one to compose different types of graph convolutions in the same model.

From Local to Global Convolutions

The methods we’ve seen so far perform ‘local’ convolutions:
every node’s feature is updated using a function of its local neighbours’ features.

While performing enough steps of message-passing will eventually ensure that
information from all nodes in the graph is passed,
one may wonder if there are more direct ways to perform ‘global’ convolutions.

The answer is yes; we will now describe an approach that was actually first put forward
in the context of neural networks by ,
much before any of the GNN models we looked at above.

Spectral Convolutions

As before, we will focus on the case where nodes have one-dimensional features.
After choosing an arbitrary node-order, we can stack all of the node features to get a
‘feature vector’

xRnx in mathbb{R}^n

Key Idea:
Given a feature vector

xx

,
the Laplacian

LL

allows us to quantify how smooth

xx

is, with respect to

GG

.

How?

After normalizing

xx

such that

i=1nxi2=1sum_{i = 1}^n x_i^2 = 1

LL

:

RLR_L

RL(x)=xTLxxTx=(i,j)E(xixj)2ixi2=(i,j)E(xixj)2.
R_L(x) = frac{x^T L x}{x^T x} = frac{sum_{(i, j) in E} (x_i – x_j)^2}{sum_i x_i^2} = sum_{(i, j) in E} (x_i – x_j)^2.

xx

that assign similar values to
adjacent nodes in

GG

(hence, are smooth) would have smaller values of

RL(x)R_L(x)

LL

is a real, symmetric matrix, which means it has all real eigenvalues

λ1λnlambda_1 leq ldots leq lambda_{n}

λlambda

of a matrix

AA

is a value
satisfying the equation

Au=λuAu = lambda u

for a certain vector

uu

, called an eigenvector.
For a friendly introduction to eigenvectors,
please see this tutorial.

Further, the corresponding eigenvectors

u1,,unu_1, ldots, u_{n}

uk1Tuk2={1 if k1=k2.0 if k1k2.
u_{k_1}^T u_{k_2} =
begin{cases}
1 quad text{ if } {k_1} = {k_2}. \
0 quad text{ if } {k_1} neq {k_2}.
end{cases}

LL

are successively less smooth, as

RLR_L

argminx, x{u1,,ui1}RL(x)=ui.minx, x{u1,,ui1}RL(x)=λi.
underset{x, x perp {u_1, ldots, u_{i – 1}}}{text{argmin}} R_L(x) = u_i.
qquad
qquad
qquad
min_{x, x perp {u_1, ldots, u_{i – 1}}} R_L(x) = lambda_i.

LL

are called its ‘spectrum’, hence the name!
We denote the ‘spectral’ decomposition of

LL

as:

L=UΛUT.
L = U Lambda U^T.


where

ΛLambda

is the diagonal matrix of sorted eigenvalues,
and

UU

denotes the matrix of the eigenvectors (sorted corresponding to increasing eigenvalues):

Λ=[λ1λn]U=[u1  un].
Lambda = begin{bmatrix}
lambda_{1} & & \
& ddots & \
& & lambda_{n}
end{bmatrix}
qquad
qquad
qquad
qquad
U = begin{bmatrix} \ u_1 cdots u_n \ end{bmatrix}.

UTU=IU^T U = I

nn

eigenvectors form a basis for

Rnmathbb{R}^n

xx

can be represented as a linear combination of these eigenvectors:

x=i=1nxi^ui=Ux^.
x = sum_{i = 1}^n hat{x_i} u_i = U hat{x}.

x^hat{x}

[x0,xn][x_0, ldots x_n]

x^hat{x}

xx

.
The orthonormality condition allows us to state:

x=Ux^UTx=x^.
x = U hat{x} quad Longleftrightarrow quad U^T x = hat{x}.

xx

and the ‘spectral’ representation

x^hat{x}

xRnx in mathbb{R}^n

Spectral Representations of Natural Images

As discussed before, we can consider any image as a grid graph, where each pixel is a node,
connected by edges to adjacent pixels.
Thus, a pixel can have either

3,5,3, 5,

or

88

neighbours, depending on its location within the image grid.
Each pixel gets a value as part of the image. If the image is grayscale, each value will be a single
real number indicating how dark the pixel is. If the image is colored, each value will be a

33

-dimensional
vector, indicating the values for the red, green and blue (RGB) channels.
We use the alpha channel as well in the visualization below, so this is actually RGBA.

This construction allows us to compute the graph Laplacian and the eigenvector matrix

UU

.
Given an image, we can then investigate what its spectral representation looks like.

To shed some light on what the spectral representation actually encodes,
we perform the following experiment over each channel of the image independently:

  • We first collect all pixel values across a channel into a feature vector

    xx

    .

  • Then, we obtain its spectral representation

    x^hat{x}

    x^=UTx
    hat{x} = U^T x

  • We truncate this to the first

    mm

    components to get

    x^mhat{x}_m

    nmn – m

    components of

    x^hat{x}

    mm

    eigenvectors to compute the spectral representation.

    x^m=Truncatem(x^)
    hat{x}_m = text{Truncate}_m(hat{x})

  • Then, we convert this truncated representation

    x^mhat{x}_m

    xmx_m

    xm=Ux^m
    x_m = U hat{x}_m

Finally, we stack the resulting channels back together to get back an image.
We can now see how the resulting image changes with choices of

mm

.
Note that when

m=nm = n

, the resulting image is identical to the original image,
as we can reconstruct each channel exactly.

Use the radio buttons at the top to chose one of the four sample images.
Each of these images has been taken from the ImageNet
dataset and downsampled to

5050

pixels wide and

4040

pixels tall.
As there are

n=50×40=2000n = 50 times 40 = 2000

pixels in each image, there are

20002000

Laplacian eigenvectors.
Use the slider at the bottom to change the number of spectral components to keep, noting how
images get progressively blurrier as the number of components decrease.

As

mm

decreases, we see that the output image

xmx_m

mm

to

11

, the output image

xmx_m

nn

components;
we can retain a lot of the information in the image with significantly fewer components.

We can relate this to the Fourier decomposition of images:
the more eigenvectors we use, the higher frequencies we can represent on the grid.

To complement the visualization above,
we additionally visualize the first few eigenvectors on a smaller

8×88 times 8

grid below.
We change the coefficients of the first

1010

out of

6464

eigenvectors
in the spectral representation
and see how the resulting image changes:

Move the sliders to change the spectral representation

x^hat{x}

xx

itself changes on the image (left).
Note how the first eigenvectors are much ‘smoother’ than the later ones,
and the many patterns we can make with only

1010

eigenvectors.

These visualizations should convince you that the first eigenvectors are indeed smooth,
and the smoothness correspondingly decreases as we consider later eigenvectors.

For any image

xx

, we can think of
the initial entries of the spectral representation

x^hat{x}

Embedding Computation

We now have the background to understand spectral convolutions
and how they can be used to compute embeddings/feature representations of nodes.

As before, the model we describe below has

KK

layers:
each layer

kk

has learnable parameters

w^(k)hat{w}^{(k)}

mm

, the number of
eigenvectors used to compute the spectral representations.
We had shown in the previous section that we can take

mnm ll n


and still not lose out on significant amounts of information.

Thus, convolution in the spectral domain enables the use of significantly fewer parameters
than just direct convolution in the natural domain.
Further, by virtue of the smoothness of the Laplacian eigenvectors across the graph,
using spectral representations automatically enforces an inductive bias for
neighbouring nodes to get similar representations.

Assuming one-dimensional node features for now,
the output of each layer is a vector of node representations

h(k)h^{(k)}

We fix an ordering of the nodes in

GG

. This gives us the adjacency matrix

AA

and the graph Laplacian

LL

,
allowing us to compute

UmU_m

The method above generalizes easily to the case where each

h(k)Rdkh^{(k)} in mathbb{R}^{d_k}

With the insights from the previous section, we see that convolution in the spectral-domain of graphs
can be thought of as the generalization of convolution in the frequency-domain of images.

Spectral Convolutions are Node-Order Equivariant

We can show spectral convolutions are node-order equivariant using a similar approach
as for Laplacian polynomial filters.


Details for the Interested Reader

As in our proof before,
let’s fix an arbitrary node-order.
Then, any other node-order can be represented by a
permutation of this original node-order.
We can associate this permutation with its permutation matrix

PP

.

Under this new node-order,
the quantities below transform in the following way:

xPxAPAPTLPLPTUmPUm
begin{aligned}
x &to Px \
A &to PAP^T \
L &to PLP^T \
U_m &to PU_m
end{aligned}

x^(PUm)T(Px)=UmTx=x^w^(PUm)T(Pw)=UmTw=w^g^g^g(PUm)g^=P(Umg^)=Pg
begin{aligned}
hat{x} &to left(PU_mright)^T (Px) = U_m^T x = hat{x} \
hat{w} &to left(PU_mright)^T (Pw) = U_m^T w = hat{w} \
hat{g} &to hat{g} \
g &to (PU_m)hat{g} = P(U_mhat{g}) = Pg
end{aligned}

σsigma

is applied elementwise:

f(Px)=σ(Pg)=Pσ(g)=Pf(x)
f(Px) = sigma(Pg) = P sigma(g) = P f(x)


as required.
Further, we see that the spectral quantities

x^,w^hat{x}, hat{w}

g^hat{g}

The theory of spectral convolutions is mathematically well-grounded;
however, there are some key disadvantages that we must talk about:

  • We need to compute the eigenvector matrix

    UmU_m

    LL

    . For large graphs, this becomes quite infeasible.

  • Even if we can compute

    UmU_m

    UmU_m

    UmTU_m^T

  • The learned filters are specific to the input graphs,
    as they are represented in terms
    of the spectral decomposition of input graph Laplacian

    LL

    .
    This means they do not transfer well to new graphs
    which have significantly different structure (and hence, significantly
    different eigenvalues) .

While spectral convolutions have largely been superseded by
‘local’ convolutions for the reasons discussed above,
there is still much merit to understanding the ideas behind them.
Indeed, a recently proposed GNN model called Directional Graph Networks

actually uses the Laplacian eigenvectors
and their mathematical properties
extensively.

Global Propagation via Graph Embeddings

A simpler way to incorporate graph-level information
is to compute embeddings of the entire graph by pooling node
(and possibly edge) embeddings,
and then using the graph embedding to update node embeddings,
following an iterative scheme similar to what we have looked at here.
This is an approach used by Graph Networks
.
We will briefly discuss how graph-level embeddings
can be constructed in Pooling.
However, such approaches tend to ignore the underlying
topology of the graph that spectral convolutions can capture.

Learning GNN Parameters

All of the embedding computations we’ve described here, whether spectral or spatial, are completely differentiable.
This allows GNNs to be trained in an end-to-end fashion, just like a standard neural network,
once a suitable loss function

Lmathcal{L}

is defined:

  • Node Classification: By minimizing any of the standard losses for classification tasks,
    such as categorical cross-entropy when multiple classes are present:

    L(yv,yv^)=cyvclogyvc^.
    mathcal{L}(y_v, hat{y_v}) = -sum_{c} y_{vc} log{hat{y_{vc}}}.

    yvc^hat{y_{vc}}

    vv

    is in class

    cc

    .
    GNNs adapt well to the semi-supervised setting, which is when only some nodes in the graph are labelled.
    In this setting, one way to define a loss

    LGmathcal{L}_{G}

    GG

    is:

    LG=vLab(G)L(yv,yv^)Lab(G)
    mathcal{L}_{G} = frac{sumlimits_{v in text{Lab}(G)} mathcal{L}(y_v, hat{y_v})}{| text{Lab}(G) |}

    Lab(G)text{Lab}(G)

    .

  • Graph Classification: By aggregating node representations,
    one can construct a vector representation of the entire graph.
    This graph representation can be used for any graph-level task, even beyond classification.
    See Pooling for how representations of graphs can be constructed.
  • Link Prediction: By sampling pairs of adjacent and non-adjacent nodes,
    and use these vector pairs as inputs to predict the presence/absence of an edge.
    For a concrete example, by minimizing the following ‘logistic regression’-like loss:

    L(yv,yu,evu)=evulog(pvu)(1evu)log(1pvu)pvu=σ(yvTyu)
    begin{aligned}
    mathcal{L}(y_v, y_u, e_{vu}) &= -e_{vu} log(p_{vu}) – (1 – e_{vu}) log(1 – p_{vu}) \
    p_{vu} &= sigma(y_v^Ty_u)
    end{aligned}

    σsigma

    is the sigmoid function,
    and

    evu=1e_{vu} = 1

    vv

    and

    uu

    , being

    00

    otherwise.

  • Node Clustering: By simply clustering the learned node representations.

The broad success of pre-training for natural language processing models
such as ELMo and BERT
has sparked interest in similar techniques for GNNs
.
The key idea in each of these papers is to train GNNs to predict
local (eg. node degrees, clustering coefficient, masked node attributes)
and/or global graph properties (eg. pairwise distances, masked global attributes).

Another self-supervised technique is to enforce that neighbouring nodes get similar embeddings,
mimicking random-walk approaches such as node2vec and DeepWalk :

LG=vuNR(v)logexpzvTzuuexpzuTzu.
L_{G} = sum_{v} sum_{u in N_R(v)} logfrac{exp{z_v^T z_u}}{sumlimits_{u’} exp{z_{u’}^T z_u}}.

where

NR(v)N_R(v)

vv

.
For large graphs, where computing the sum over all nodes may be computationally expensive,
techniques such as Noise Contrastive Estimation are especially useful.

Conclusion and Further Reading

While we have looked at many techniques and ideas in this article,
the field of Graph Neural Networks is extremely vast.
We have been forced to restrict our discussion to a small subset of the entire literature,
while still communicating the key ideas and design principles behind GNNs.
We recommend the interested reader take a look at
for a more comprehensive survey.

We end with pointers and references for additional concepts readers might be interested in:

GNNs in Practice

It turns out that accomodating the different structures of graphs is often hard to do efficiently,
but we can still represent many GNN update equations using
as sparse matrix-vector products (since generally, the adjacency matrix is sparse for most real-world graph datasets.)
For example, the GCN variant discussed here can be represented as:

h(k)=D1Ah(k1)W(k)T+h(k1)B(k)T.
h^{(k)} = D^{-1} A cdot h^{(k – 1)} {W^{(k)}}^T + h^{(k – 1)} {B^{(k)}}^T.

Regularization techniques for standard neural networks,
such as Dropout ,
can be applied in a straightforward manner to the parameters
(for example, zero out entire rows of

W(k)W^{(k)}

Different Kinds of Graphs

Here, we have focused on undirected graphs, to avoid going into too many unnecessary details.
However, there are some simple variants of spatial convolutions for:

  • Directed graphs: Aggregate across in-neighbourhood and/or out-neighbourhood features.
  • Temporal graphs: Aggregate across previous and/or future node features.
  • Heterogeneous graphs: Learn different aggregation functions for each node/edge type.

There do exist more sophisticated techniques that can take advantage of the different structures of these graphs:
see for more discussion.

Pooling

This article discusses how GNNs compute useful representations of nodes.
But what if we wanted to compute representations of graphs for graph-level tasks (for example, predicting the toxicity of a molecule)?

A simple solution is to just aggregate the final node embeddings and pass them through another neural network

PREDICTGtext{PREDICT}_G

hG=PREDICTG(AGGvG({hv}))
h_G = text{PREDICT}_G Big( text{AGG}_{v in G}left({ h_v } right) Big)

  • SortPool: Sort vertices of the graph to get a fixed-size node-order invariant representation of the graph, and then apply any standard neural network architecture.
  • DiffPool: Learn to cluster vertices, build a coarser graph over clusters instead of nodes, then apply a GNN over the coarser graph. Repeat until only one cluster is left.
  • SAGPool: Apply a GNN to learn node scores, then keep only the nodes with the top scores, throwing away the rest. Repeat until only one node is left.

Supplementary Material

Reproducing Experiments

The experiments from
Spectral Representations of Natural Images
can be reproduced using the following
Colab Google Colaboratory notebook:
Spectral Representations of Natural Images.

Recreating Visualizations

To aid in the creation of future interactive articles,
we have created ObservableHQ
ObservableHQ
notebooks for each of the interactive visualizations here:

[ad_2]

Source link

Spread the Word!