Tang, Minh, Sussman, Daniel L., Priebe, Carey E.

In this work we show that, using the eigen-decomposition of the adjacency matrix, we can consistently estimate feature maps for latent position graphs with positive definite link function $\kappa$, provided that the latent positions are i.i.d. from some distribution F. We then consider the exploitation task of vertex classification where the link function $\kappa$ belongs to the class of universal kernels and class labels are observed for a number of vertices tending to infinity and that the remaining vertices are to be classified. We show that minimization of the empirical $\varphi$-risk for some convex surrogate $\varphi$ of 0-1 loss over a class of linear classifiers with increasing complexities yields a universally consistent classifier, that is, a classification rule with error converging to Bayes optimal for any distribution F.

In many learning problems, the learning system is presented with values for features that are actually irrelevant to the concept it is trying to learn. The FOCUS algorithm, due to Almuallim and Dietterich, performs an explicit search for the smallest possible input feature set S that permits a consistent mapping from the features in S to the output feature. The FOCUS algorithm can also be seen as an algorithm for learning determinations or functional dependencies, as suggested in [6]. Another algorithm for learning determinations appears in [7]. The FOCUS algorithm has superpolynomial runtime, but Almuallim and Dietterich leave open the question of tractability of the underlying problem. In this paper, the problem is shown to be NPcomplete. We also describe briefly some experiments that demonstrate the benefits of determination learning, and show that finding lowest-cardinality determinations is easier in practice than finding minimal determinations.

Triebel, Rudolph A. (University of Oxford) | Paul, Rohan (University of Oxford) | Rus, Daniela (Massachusetts Institute of Technology) | Newman, Paul (University of Oxford)

In this paper, we address the problem of continually parsing a stream of 3D point cloud data acquired from a laser sensor mounted on a road vehicle. We leverage an online star clustering algorithm coupled with an incremental belief update in an evolving undirected graphical model. The fusion of these techniques allows the robot to parse streamed data and to continually improve its understanding of the world. The core competency produced is an ability to infer object classes from similarities based on appearance and shape features, and to concurrently combine that with a spatial smoothing algorithm incorporating geometric consistency. This formulation of feature-space star clustering modulating the potentials of a spatial graphical model is entirely novel. In our method, the two sources of information: feature similarity and geometrical consistency are fed continu- ally into the system, improving the belief over the class distributions as new data arrives. The algorithm obviates the need for hand-labeled training data and makes no apriori assumptions on the number or characteristics of object categories. Rather, they are learnt incrementally over time from streamed input data. In experiments per- formed on real 3D laser data from an outdoor scene, we show that our approach is capable of obtaining an ever- improving unsupervised scene categorization.

Platanios, Emmanouil Antonios, Smola, Alex

We propose an algorithm for deep learning on networks and graphs. It relies on the notion that many graph algorithms, such as PageRank, Weisfeiler-Lehman, or Message Passing can be expressed as iterative vertex updates. Unlike previous methods which rely on the ingenuity of the designer, Deep Graphs are adaptive to the estimation problem. Training and deployment are both efficient, since the cost is $O(|E| + |V|)$, where $E$ and $V$ are the sets of edges and vertices respectively. In short, we learn the recurrent update functions rather than positing their specific functional form. This yields an algorithm that achieves excellent accuracy on both graph labeling and regression tasks.

Bai, Lu, Cui, Lixin, Wu, Shu, Jiao, Yuhang, Hancock, Edwin R.

In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of fixed-sized one-dimensional convolution filters on the grid structure. We show that the proposed model not only integrates the precise structural correspondence information between graphs but also minimises the loss of structural information residing on local-level vertices. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model.