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.
Introducing variability while maintaining coherence is a core task in learning to generate utterances in conversation. Standard neural encoder-decoder models and their extensions using conditional variational autoencoder often result in either trivial or digressive responses. To overcome this, we explore a novel approach that injects variability into neural encoder-decoder via the use of external memory as a mixture model, namely Variational Memory Encoder-Decoder (VMED). By associating each memory read with a mode in the latent mixture distribution at each timestep, our model can capture the variability observed in sequential data such as natural conversations. We empirically compare the proposed model against other recent approaches on various conversational datasets. The results show that VMED consistently achieves significant improvement over others in both metric-based and qualitative evaluations.
Generative Adversarial Networks (GAN) are one of the most prominent tools for learning complicated distributions. However, problems such as mode collapse and catastrophic forgetting, prevent GAN from learning the target distribution. These problems are usually studied independently from each other. In this paper, we show that both problems are present in GAN and their combined effect makes the training of GAN unstable. We also show that methods such as gradient penalties and momentum based optimizers can improve the stability of GAN by effectively preventing these problems from happening. Finally, we study a mechanism for mode collapse to occur and propagate in feedforward neural networks.
We address a largely open problem of multilabel classification over graphs. Unlike traditional vector input, a graph has rich variable-size substructures which are related to the labels in some ways. We believe that uncovering these relations might hold the key to classification performance and explainability. We introduce GAML (Graph Attentional Multi-Label learning), a novel graph neural network that can handle this problem effectively. GAML regards labels as auxiliary nodes and models them in conjunction with the input graph. By applying message passing and attention mechanisms to both the label nodes and the input nodes iteratively, GAML can capture the relations between the labels and the input subgraphs at various resolution scales. Moreover, our model can take advantage of explicit label dependencies. It also scales linearly with the number of labels and graph size thanks to our proposed hierarchical attention. We evaluate GAML on an extensive set of experiments with both graph-structured inputs and classical unstructured inputs. The results show that GAML significantly outperforms other competing methods. Importantly, GAML enables intuitive visualizations for better understanding of the label-substructure relations and explanation of the model behaviors.
Machine-assisted treatment recommendations hold a promise to reduce physician time and decision errors. We formulate the task as a sequence-to-sequence prediction model that takes the entire time-ordered medical history as input, and predicts a sequence of future clinical procedures and medications. It is built on the premise that an effective treatment plan may have long-term dependencies from previous medical history. We approach the problem by using a memory-augmented neural network, in particular, by leveraging the recent differentiable neural computer that consists of a neural controller and an external memory module. But differing from the original model, we use dual controllers, one for encoding the history followed by another for decoding the treatment sequences. In the encoding phase, the memory is updated as new input is read; at the end of this phase, the memory holds not only the medical history but also the information about the current illness. During the decoding phase, the memory is write-protected. The decoding controller generates a treatment sequence, one treatment option at a time. The resulting dual controller write-protected memory-augmented neural network is demonstrated on the MIMIC-III dataset on two tasks: procedure prediction and medication prescription. The results show improved performance over both traditional bag-of-words and sequence-to-sequence methods.
One of the core tasks in multi-view learning is to capture relations among views. For sequential data, the relations not only span across views, but also extend throughout the view length to form long-term intra-view and inter-view interactions. In this paper, we present a new memory augmented neural network model that aims to model these complex interactions between two asynchronous sequential views. Our model uses two encoders for reading from and writing to two external memories for encoding input views. The intra-view interactions and the long-term dependencies are captured by the use of memories during this encoding process. There are two modes of memory accessing in our system: late-fusion and early-fusion, corresponding to late and early inter-view interactions. In the late-fusion mode, the two memories are separated, containing only view-specific contents. In the early-fusion mode, the two memories share the same addressing space, allowing cross-memory accessing. In both cases, the knowledge from the memories will be combined by a decoder to make predictions over the output space. The resulting dual memory neural computer is demonstrated on a comprehensive set of experiments, including a synthetic task of summing two sequences and the tasks of drug prescription and disease progression in healthcare. The results demonstrate competitive performance over both traditional algorithms and deep learning methods designed for multi-view problems.
We present a new distributed representation in deep neural nets wherein the information is represented in native form as a matrix. This differs from current neural architectures that rely on vector representations. We consider matrices as central to the architecture and they compose the input, hidden and output layers. The model representation is more compact and elegant -- the number of parameters grows only with the largest dimension of the incoming layer rather than the number of hidden units. We derive several new deep networks: (i) feed-forward nets that map an input matrix into an output matrix, (ii) recurrent nets which map a sequence of input matrices into a sequence of output matrices. We also reinterpret existing models for (iii) memory-augmented networks and (iv) graphs using matrix notations. For graphs we demonstrate how the new notations lead to simple but effective extensions with multiple attentions. Extensive experiments on handwritten digits recognition, face reconstruction, sequence to sequence learning, EEG classification, and graph-based node classification demonstrate the efficacy and compactness of the matrix architectures.
Modern healthcare is ripe for disruption by AI. A game changer would be automatic understanding the latent processes from electronic medical records, which are being collected for billions of people worldwide. However, these healthcare processes are complicated by the interaction between at least three dynamic components: the illness which involves multiple diseases, the care which involves multiple treatments, and the recording practice which is biased and erroneous. Existing methods are inadequate in capturing the dynamic structure of care. We propose Resset, an end-to-end recurrent model that reads medical record and predicts future risk. The model adopts the algebraic view in that discrete medical objects are embedded into continuous vectors lying in the same space. We formulate the problem as modeling sequences of sets, a novel setting that have rarely, if not, been addressed. Within Resset, the bag of diseases recorded at each clinic visit is modeled as function of sets. The same hold for the bag of treatments. The interaction between the disease bag and the treatment bag at a visit is modeled in several, one of which as residual of diseases minus the treatments. Finally, the health trajectory, which is a sequence of visits, is modeled using a recurrent neural network. We report results on over a hundred thousand hospital visits by patients suffered from two costly chronic diseases -- diabetes and mental health. Resset shows promises in multiple predictive tasks such as readmission prediction, treatments recommendation and diseases progression.
Process analytics involves a sophisticated layer of data analytics built over the traditional notion of process mining. The flexible execution of business process instances involves multiple critical decisions including what task to perform next and what resources to allocate to a task. In this paper, we explore the application of deep learning techniques for solving various process analytics related problems. Based on recent advances in the field we specifically look at memory-augmented neural networks (MANN)s and adapt the latest model to date, namely the Differential Neural Computer. We introduce two modifications to account for a variety of tasks in predictive process analytics: (i) separating the encoding phase and decoding phase, resulting dual controllers, one for each phase; (ii) implementing a write-protected policy for the memory during the decoding phase. We demonstrate the feasibility and usefulness of our approach by solving a number of common process analytics tasks such as next activity prediction, time to completion and suffix prediction. We also introduce the notion of MANN based process analytics recommendation machinery that once deployed can serve as an effective business process recommendation engine enabling organizations to answer various prescriptive process analytics related questions.Using real-world datasets, we benchmark our results against those obtained from the state-of-art methods. We show that MANNs based process analytics methods can acheive state-of-the-art performance and have a lot of value to offer for enterprise specific process anlaytics applications.
Molecular activity prediction is critical in drug design. Machine learning techniques such as kernel methods and random forests have been successful for this task. These models require fixed-size feature vectors as input while the molecules are variable in size and structure. As a result, fixed-size fingerprint representation is poor in handling substructures for large molecules. In addition, molecular activity tests, or a so-called BioAssays, are relatively small in the number of tested molecules due to its complexity. Here we approach the problem through deep neural networks as they are flexible in modeling structured data such as grids, sequences and graphs. We train multiple BioAssays using a multi-task learning framework, which combines information from multiple sources to improve the performance of prediction, especially on small datasets. We propose Graph Memory Network (GraphMem), a memory-augmented neural network to model the graph structure in molecules. GraphMem consists of a recurrent controller coupled with an external memory whose cells dynamically interact and change through a multi-hop reasoning process. Applied to the molecules, the dynamic interactions enable an iterative refinement of the representation of molecular graphs with multiple bond types. GraphMem is capable of jointly training on multiple datasets by using a specific-task query fed to the controller as an input. We demonstrate the effectiveness of the proposed model for separately and jointly training on more than 100K measurements, spanning across 9 BioAssay activity tests.