2019

GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation

Brockschmidt, Marc

Understand

This paper presents a new Graph Neural Network (GNN) type using feature-wise linear modulation (FiLM).

Many standard GNN variants propagate information along the edges of a graph by computing "messages" based only on the representation of the source of each edge.
In GNN-FiLM, the representation of the target node of an edge is additionally used to compute a transformation that can be applied to all incoming messages, allowing feature-wise modulation of the passed information.
Results of experiments comparing different GNN architectures on three tasks from the literature are presented, based on re-implementations of baseline methods.

Collective classification in network data
Sen, P., Namata, G., Bilgic, M., Getoor, L., Galligher, B., and Eliassi-Rad, T · 2008
Earlier work this paper cites.
Quantum chemistry structures and properties of 134 kilo molecules
Ramakrishnan, R., Dral, P. O., Rupp, M., and Lilienfeld, O. A. V · 2014
Earlier work this paper cites.
Layer normalization
Original
Ba, L. J., Kiros, R., and Hinton, G. E · 2016
Earlier work this paper cites.
Gated graph sequence neural networks
Li, Y., Tarlow, D., Brockschmidt, M., and Zemel, R · 2016
Earlier work this paper cites.
Neural message passing for quantum chemistry
Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., and Dahl, G. E · 2017
Earlier work this paper cites.
HyperNetworks
Ha, D., Dai, A. M., and Le, Q. V · 2017
Earlier work this paper cites.
Inductive representation learning on large graphs
Hamilton, W. L., Ying, R., and Leskovec, J · 2017
Earlier work this paper cites.

Semi-supervised classification with graph convolutional networks
Kipf, T. N. and Welling, M · 2017
Cited alongside, same era.
FiLM: Visual reasoning with a general conditioning layer
Perez, E., Strub, F., de Vries, H., Dumoulin, V., and Courville, A. C · 2017
Cited alongside, same era.
Predicting multicellular function through multi-layer tissue networks
Zitnik, M. and Leskovec, J · 2017
Cited alongside, same era.
Learning to represent programs with graphs
Allamanis, M., Brockschmidt, M., and Khademi, M · 2018
Cited alongside, same era.
Modeling relational data with graph convolutional network
Schlichtkrull, M., Kipf, T. N., Bloem, P., van den Berg, R., Titov, I., and Welling, M · 2018
Cited alongside, same era.
Pitfalls of graph neural network evaluation
Original
Shchur, O., Mumme, M., Bojchevski, A., and Günnemann, S · 2018
Cited alongside, same era.
Graph Attention Networks
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y · 2018
Cited alongside, same era.

Fast training of sparse graph neural networks on dense hardware
Original
Balog, M., van Merriënboer, B., Moitra, S., Li, Y., and Tarlow, D · 2019
Closest in time.
Relational graph attention networks
Original
Busbridge, D., Sherburn, D., Cavallo, P., and Hammerla, N. Y · 2019
Closest in time.
Open vocabulary learning on source code with a graph-structured cache
Cvitkovic, M., Singh, B., and Anandkumar, A · 2019
Closest in time.
Graph representations for higher-order logic and theorem proving
Original
Paliwal, A., Loos, S. M., Rabe, M. N., Bansal, K., and Szegedy, C · 2019
Closest in time.
Learning a SAT solver from single-bit supervision
Selsam, D., Lamm, M., Bünz, B., Liang, P., de Moura, L., and Dill, D. L · 2019
Closest in time.
Pay less attention with lightweight and dynamic convolutions
Wu, F., Fan, A., Baevski, A., Dauphin, Y., and Auli, M · 2019
Closest in time.
How powerful are graph neural networks?
Xu, K., Hu, W., Leskovec, J., and Jegelka, S · 2019
Closest in time.

alphaXiv searches the wider corpus for related work and actual follow-ups.

alphaXiv is searching for related work…

Reading the bibliography…