Molecule Property Prediction and Classification with Graph Hypernetworks
This work addresses a stability issue in hypernetworks for computational chemistry, offering a generic solution that can replace domain-specific methods, though it appears incremental.
The authors tackled the problem of training instability in hypernetworks for molecule property prediction by combining current and first messages, achieving state-of-the-art results in various benchmarks.
Graph neural networks are currently leading the performance charts in learning-based molecule property prediction and classification. Computational chemistry has, therefore, become the a prominent testbed for generic graph neural networks, as well as for specialized message passing methods. In this work, we demonstrate that the replacement of the underlying networks with hypernetworks leads to a boost in performance, obtaining state of the art results in various benchmarks. A major difficulty in the application of hypernetworks is their lack of stability. We tackle this by combining the current message and the first message. A recent work has tackled the training instability of hypernetworks in the context of error correcting codes, by replacing the activation function of the message passing network with a low-order Taylor approximation of it. We demonstrate that our generic solution can replace this domain-specific solution.