Relational dynamic memory networks
This addresses the problem of handling structured data in AI for domains like software security and bioinformatics, representing an incremental improvement over existing memory-augmented neural networks.
The paper tackles the challenge of representing and manipulating complex graph-structured data by introducing Relational Dynamic Memory Networks (RMDN), a memory-augmented neural network with structured multi-relational graph memory, which learns to answer queries without explicit programming and shows efficacy on tasks like software vulnerability and molecular bioactivity prediction.
Neural networks excel in detecting regular patterns but are less successful in representing and manipulating complex data structures, possibly due to the lack of an external memory. This has led to the recent development of a new line of architectures known as Memory-Augmented Neural Networks (MANNs), each of which consists of a neural network that interacts with an external memory matrix. However, this RAM-like memory matrix is unstructured and thus does not naturally encode structured objects. Here we design a new MANN dubbed Relational Dynamic Memory Network (RMDN) to bridge the gap. Like existing MANNs, RMDN has a neural controller but its memory is structured as multi-relational graphs. RMDN uses the memory to represent and manipulate graph-structured data in response to query; and as a neural network, RMDN is trainable from labeled data. Thus RMDN learns to answer queries about a set of graph-structured objects without explicit programming. We evaluate the capability of RMDN on several important prediction problems, including software vulnerability, molecular bioactivity and chemical-chemical interaction. Results demonstrate the efficacy of the proposed model.