When solving an equation, using the result to encode a message, transmitting the coded message to another device, decoding the message at the other end, saving the message onto a hard drive, or using it to create a visual rendering; inaccuracies are often the system's enemy and have to be fought against. Furthermore, if and when any of these computational operations is repeated, we expect the results to be unchanged. We view an unrepeatable result as a sign of a "bug" that either has to be fixed, tamed, or at least well understood and tolerated. Reduced precision and reliability is often considered as a price in the tradeoff with computational efficiency. The central thesis of this perspective article is that for machine learning (ML) specifically, and artificial intelligence (AI) more generally, probabilistic operations are fundamentally important building blocks, which the field is growing to rely on. We anticipate that stochasticity will therefore feature more prominently, and as a fundamental principle, in the future of machine intelligence.

Bike sharing systems (BSS) have been a popular traveling service for years and are used worldwide. It is attractive for cities and users who wants to promote healthier lifestyles; to reduce air pollution and greenhouse gas emission as well as improve traffic. One major challenge to docked bike sharing system is redistributing bikes and balancing dock stations. Some studies propose models that can help forecasting bike usage; strategies for rebalancing bike distribution; establish patterns or how to identify patterns. Other studies propose to extend the approach by including weather data. This study aims to extend upon these proposals and opportunities to explore how and in what magnitude weather impacts bike usage. Bike usage data and weather data are gathered for the city of Washington D.C. and are analyzed using k-means clustering algorithm. K-means managed to identify three clusters that correspond to bike usage depending on weather conditions. The results show that the weather impact on bike usage was noticeable between clusters. It showed that temperature followed by precipitation weighted the most, out of five weather variables.

The advisor-advisee relationship represents direct knowledge heritage, and such relationship may not be readily available from academic libraries and search engines. This work aims to discover advisor-advisee relationships hidden behind scientific collaboration networks. For this purpose, we propose a novel model based on Network Representation Learning (NRL), namely Shifu2, which takes the collaboration network as input and the identified advisor-advisee relationship as output. In contrast to existing NRL models, Shifu2 considers not only the network structure but also the semantic information of nodes and edges. Shifu2 encodes nodes and edges into low-dimensional vectors respectively, both of which are then utilized to identify advisor-advisee relationships. Experimental results illustrate improved stability and effectiveness of the proposed model over state-of-the-art methods. In addition, we generate a large-scale academic genealogy dataset by taking advantage of Shifu2.

We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current limitations of the literature: i) The model is inductive: it can embed new graphs without re-training in the presence of new data; ii) The method takes into account both micro-structures and macro-structures by looking at the attributed graphs at different scales; iii) The model is end-to-end differentiable: it is a building block that can be plugged into deep learning pipelines and allows for back-propagation. We show that combining a coarsening method having strong theoretical guarantees with mutual information maximization suffices to produce high quality embeddings. We evaluate them on classification tasks with common benchmarks of the literature. We show that our algorithm is competitive with state of the art among unsupervised graph representation learning methods.

A graph neural network (GNN) is a good choice for predicting the chemical properties of molecules. Compared with other deep networks, however, the current performance of a GNN is limited owing to the "curse of depth." Inspired by long-established feature engineering in the field of chemistry, we expanded an atom representation using Weisfeiler-Lehman (WL) embedding, which is designed to capture local atomic patterns dominating the chemical properties of a molecule. In terms of representability, we show WL embedding can replace the first two layers of ReLU GNN -- a normal embedding and a hidden GNN layer -- with a smaller weight norm. We then demonstrate that WL embedding consistently improves the empirical performance over multiple GNN architectures and several molecular graph datasets.

The skip-gram model for learning word embeddings (Mikolov et al. 2013) has been widely popular, and DeepWalk (Perozzi et al. 2014), among other methods, has extended the model to learning node representations from networks. Recent work of Qiu et al. (2018) provides a closed-form expression for the DeepWalk objective, obviating the need for sampling for small datasets and improving accuracy. In these methods, the "window size" T within which words or nodes are considered to co-occur is a key hyperparameter. We study the objective in the limit as T goes to infinity, which allows us to simplify the expression of Qiu et al. We prove that this limiting objective corresponds to factoring a simple transformation of the pseudoinverse of the graph Laplacian, linking DeepWalk to extensive prior work in spectral graph embeddings. Further, we show that by a applying a simple nonlinear entrywise transformation to this pseudoinverse, we recover a good approximation of the finite-T objective and embeddings that are competitive with those from DeepWalk and other skip-gram methods in multi-label classification. Surprisingly, we find that even simple binary thresholding of the Laplacian pseudoinverse is often competitive, suggesting that the core advancement of recent methods is a nonlinearity on top of the classical spectral embedding approach.

Mobile authentication using behavioral biometrics has been an active area of research. Existing research relies on building machine learning classifiers to recognize an individual's unique patterns. However, these classifiers are not powerful enough to learn the discriminative features. When implemented on the mobile devices, they face new challenges from the behavioral dynamics, data privacy and side-channel leaks. To address these challenges, we present a new framework to incorporate training on battery-powered mobile devices, so private data never leaves the device and training can be flexibly scheduled to adapt the behavioral patterns at runtime. We re-formulate the classification problem into deep metric learning to improve the discriminative power and design an effective countermeasure to thwart side-channel leaks by embedding a noise signature in the sensing signals without sacrificing too much usability. The experiments demonstrate authentication accuracy over 95% on three public datasets, a sheer 15% gain from multi-class classification with less data and robustness against brute-force and side-channel attacks with 99% and 90% success, respectively. We show the feasibility of training with mobile CPUs, where training 100 epochs takes less than 10 mins and can be boosted 3-5 times with feature transfer. Finally, we profile memory, energy and computational overhead. Our results indicate that training consumes lower energy than watching videos and slightly higher energy than playing games.

Let us start with an easy example, say you are teaching a kid to differentiate dogs from cats. How would you do it? You may show him/her a dog and say "here is a dog" and when you encounter a cat you would point it out as a cat. When you show the kid enough dogs and cats, he may learn to differentiate between them. If he is trained well, he may be able to recognise different breeds of dogs which he hasn't even seen. Similarly, in Supervised Learning, we have two sets of variables.

This study introduces SECODA, a novel general-purpose unsupervised non-parametric anomaly detection algorithm for datasets containing continuous and categorical attributes. The method is guaranteed to identify cases with unique or sparse combinations of attribute values. Continuous attributes are discretized repeatedly in order to correctly determine the frequency of such value combinations. The concept of constellations, exponentially increasing weights and discretization cut points, as well as a pruning heuristic are used to detect anomalies with an optimal number of iterations. Moreover, the algorithm has a low memory imprint and its runtime performance scales linearly with the size of the dataset. An evaluation with simulated and real-life datasets shows that this algorithm is able to identify many different types of anomalies, including complex multidimensional instances. An evaluation in terms of a data quality use case with a real dataset demonstrates that SECODA can bring relevant and practical value to real-world settings.

Learning how to predict future events from patterns of past events is difficult when the set of possible event types is large. Training an unrestricted neural model might overfit to spurious patterns. To exploit domain-specific knowledge of how past events might affect an event's present probability, we propose using a temporal deductive database to track structured facts over time. Rules serve to prove facts from other facts and from past events. Each fact has a time-varying state---a vector computed by a neural net whose topology is determined by the fact's provenance, including its experience of past events. The possible event types at any time are given by special facts, whose probabilities are neurally modeled alongside their states. In both synthetic and real-world domains, we show that neural probabilistic models derived from concise Datalog programs improve prediction by encoding appropriate domain knowledge in their architecture.