Log In Sign Up

Attentional Multilabel Learning over Graphs - A message passing approach

by   Kien Do, et al.

We address a largely open problem of multilabel classification over graphs. Unlike traditional vector input, a graph has rich variable-size structures, that suggests complex relationships between labels and subgraphs. Uncovering these relations might hold the keys of classification performance and explainability. To this end, we design GAML (Graph Attentional Multi-Label learning), a graph neural network that models the relations present in the input graph, in the label set, and across graph-labels by leveraging the message passing algorithm and attention mechanism. Representation of labels and input nodes is refined iteratively through multiple steps, during which interesting subgraph-label patterns emerge. In addition, GAML is highly flexible by allowing explicit label dependencies to be incorporated easily. It also scales linearly with the number of labels and graph size thanks to our proposed hierarchical attention. These properties open a wide range of applications seen in the real world. We evaluate GAML on an extensive set of experiments with both graph inputs (for predicting drug-protein binding, and drug-cancer response), and classical unstructured inputs. The results are significantly better than well-known multilabel learning techniques.


Neural Message Passing for Multi-Label Classification

Multi-label classification (MLC) is the task of assigning a set of targe...

Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning

We propose Dynamically Pruned Message Passing Networks (DPMPN) for large...

PiNet: A Permutation Invariant Graph Neural Network for Graph Classification

We propose an end-to-end deep learning learning model for graph classifi...

Learning Graph Neural Networks with Noisy Labels

We study the robustness to symmetric label noise of GNNs training proced...

Message Passing Neural Networks for Hypergraphs

Hypergraph representations are both more efficient and better suited to ...

Deep Message Passing on Sets

Modern methods for learning over graph input data have shown the fruitfu...

SHINE: SubHypergraph Inductive Neural nEtwork

Hypergraph neural networks can model multi-way connections among nodes o...