We address a fundamental problem in chemistry known as chemical reaction product prediction. Our main insight is that the input reactant and reagent molecules can be jointly represented as a graph, and the process of generating product molecules from reactant molecules can be formulated as a sequence of graph transformations. To this end, we propose Graph Transformation Policy Network (GTPN) -a novel generic method that combines the strengths of graph neural networks and reinforcement learning to learn the reactions directly from data with minimal chemical knowledge. Compared to previous methods, GTPN has some appealing properties such as: end-to-end learning, and making no assumption about the length or the order of graph transformations. In order to guide model search through the complex discrete space of sets of bond changes effectively, we extend the standard policy gradient loss by adding useful constraints. Evaluation results show that GTPN improves the top-1 accuracy over the current state-of-the-art method by about 3and prediction errors are also analyzed carefully in the paper.Recent state-of-the-art methods (Jin et al., 2017; Bradshaw et al., 2018) have built the first capability by leveraging graph neural networks (Duvenaud et al., 2015; Hamilton et al., 2017; Pham et al., 2017; Gilmer et al., 2017). However, these methods are either unaware of the valid sets of reaction triples (Jin et al., 2017) or limited to sequences of reaction triples with a predefined orders (Bradshaw et al., 2018). The main challenge is that the space of all possible configurations of reaction triples is extremely large and non-differentiable. Moreover, a small change in the predicted set of reaction triples can lead to very different reaction products and a little mistake can produce invalid prediction.In this paper, we propose a novel method called Graph Transformation Policy Network (GTPN) that addresses the aforementioned challenges. Our model consists of three main components: a graph neural network (GNN), a node pair prediction network (NPPN) and a policy network (PN). Starting 1 . No electron left behind: a rule-based expert system to predict chemical reactions and reaction mechanisms. Journal of chemical information and modeling, 49 (9):

No abstract

Anomalies are those deviating from the norm. Unsupervised anomaly detection often translates to identifying low density regions. Major problems arise when data is high-dimensional and mixed of discrete and continuous attributes. We propose MIXMAD, which stands for MIXed data Multilevel Anomaly Detection, an ensemble method that estimates the sparse regions across multiple levels of abstraction of mixed data. The hypothesis is for domains where multiple data abstractions exist, a data point may be anomalous with respect to the raw representation or more abstract representations. To this end, our method sequentially constructs an ensemble of Deep Belief Nets (DBNs) with varying depths. Each DBN is an energy-based detector at a predefined abstraction level. At the bottom level of each DBN, there is a Mixed-variate Restricted Boltzmann Machine that models the density of mixed data. Predictions across the ensemble are finally combined via rank aggregation. The proposed MIXMAD is evaluated on high-dimensional real-world datasets of different characteristics. The results demonstrate that for anomaly detection, (a) multilevel abstraction of highdimensional and mixed data is a sensible strategy, and (b) empirically, MIXMAD is superior to popular unsupervised detection methods for both homogeneous and mixed data.

Abstract. Outlier detection amounts to finding data points that differ significantly from the norm. Classic outlier detection methods are largely designed for single data type such as continuous or discrete. However, real world data is increasingly heterogeneous, where a data point can have both discrete and continuous attributes. Handling mixed-type data in a disciplined way remains a great challenge. In this paper, we propose a new unsupervised outlier detection method for mixed-type data based on Mixed-variate Restricted Boltzmann Machine (Mv.RBM). The Mv.RBM is a principled probabilistic method that models data density. We propose to use free-energy derived from Mv.RBM as outlier score to detect outliers as those data points lying in low density regions. The method is fast to learn and compute, is scalable to massive datasets. At the same time, the outlier score is identical to data negative log-density up-to an additive constant. We evaluate the proposed method on synthetic and real-world datasets and demonstrate that (a) a proper handling mixedtypes is necessary in outlier detection, and (b) free-energy of Mv.RBM is a powerful and efficient outlier scoring method, which is highly competitive against state-of-the-arts.

No abstract