We present a probabilistic framework for overlapping community discovery and link prediction for relational data, given as a graph. The proposed framework has: (1) a deep architecture which enables us to infer multiple layers of latent features/communities for each node, providing superior link prediction performance on more complex networks and better interpretability of the latent features; and (2) a regression model which allows directly conditioning the node latent features on the side information available in form of node attributes. Our framework handles both (1) and (2) via a clean, unified model, which enjoys full local conjugacy via data augmentation, and facilitates efficient inference via closed form Gibbs sampling. Moreover, inference cost scales in the number of edges which is attractive for massive but sparse networks. Our framework is also easily extendable to model weighted networks with count-valued edges. We compare with various state-of-the-art methods and report results, both quantitative and qualitative, on several benchmark data sets.

A little striped fish that lives among rocks in Lake Tanganyika in East Africa has the unexpected ability to recognise individual faces, which it uses to keep menacing strangers in sight. The cichlid (Julidochromis transcriptus) identifies unfamiliar individuals by looking at the pattern around their eyes rather than at other body parts such as their fins or trunk, researchers have discovered. While facial recognition has been tested in some mammals, including apes, and in birds, animals such as fish or wasps were erroneously thought to have brains too simple for the task. After recent research showed that aquarium fish can be thought to identify the faces of their human owners, the Tanganyikan cichlid has now demonstrated how facial recognition is used in the wild. Because the fish lives in rock crevices hidden by vegetation on the lakebed, only a small part of its body tends to be visible at any given time.

Machine learning is going to alter our world fundamentally for the better, improving healthcare and the manufacturing industry, and assisting in the prediction of supply and demand levels across a range of industries. For those who are into science-fiction, the term "machine learning" immediately conjures up images of computers taking over the world, either to send murderous terminators from the future to our present or to place us all inside the Matrix as living power batteries. Fortunately, the truth about machine learning is not only far more prosaic, but also much more promising for the future of the human race. Basically, machine learning uses algorithms that iteratively learn from data, meaning that it enables computers to find hidden insights without being explicitly programmed where to look. The iterative aspect is especially important, as it means that as the computer is exposed to new data, it is able to adapt independently.

Recent work in multi-agent path planning has provided a number of optimal and suboptimal solvers that can efficiently find solutions to problems of growing complexity. Solvers based on Conflict-Based Search (CBS) combine single-agent solvers with shared constraints between agents to find feasible solutions. Suboptimal variants of CBS introduce alternate heuristics to avoid conflicts. In this paper we study the multi-agent planning problem in the context of non-holonomic vehicles planning on a lattice. We propose that in addition to using heuristics to avoid conflicts, we can plan using a hierarchy of movement constraints to efficiently avoid conflicts. We develop a new extension to the CBS algorithm, CBS with constraint layering (CBS+CL), which iteratively applies different movement constraint models during the CBS planning process. Our results show that this approach allows us to solve for about 2.4 times more agents in the same amount of time when compared to regular CBS without using a constraint hierarchy.

One of the most successful approaches to automated planning is the translation to propositional satisfiability (SA T). We employ incremental SA T solving to increase the capabilities of several modern encodings for SA T based planning. Experiments based on benchmarks from the 2014 International Planning Competition show that an incremental approach significantly outperforms non incremental solving. Although we are using sequential scheduling of makespans, we can outperform the state-of-the-art SA T based planning system Madagascar in the number of solved instances.

In this paper we study bidirectional state space search with consistent heuristics, with a focus on obtaining sufficient conditions for node expansion, that is, conditions characterizing nodes that must be expanded by any admissible bidirectional search algorithm. We provide such conditions for front-to-front and front-to-end bidirectional search. The sufficient conditions are used to prove that the front-to-front bidirectional search algorithm BDS1 is optimally efficient, in terms of node expansion, among a broad class of bidirectional search algorithms, for a specific class of problem instances. Dechter and Pearl's well-known result on sufficient conditions for node expansion by unidirectional algorithms such as A* is shown to be a special case of our results.

Plan-Verification is the task of determining whether a plan is a solution to a given planning problem. Any plan verifier has, apart from showing that verifying plans is possible in practice, a wide range of possible applications. These include mixed-initiative planning, where a user is integrated into the planning process, and local search, e.g., for post-optimising plans or for plan repair. In addition to its practical interest, plan verification is also a problem worth investigating for theoretical reasons. Recent work showed plan verification for hierarchical planning problems to be NP-complete, as opposed to classical planning where it is in P. As such, plan verification for hierarchical planning problem was — until now — not possible. We describe the first plan verifier for hierarchical planning. It uses a translation of the problem into a SAT formula. Further we conduct an empirical evaluation, showing that the correct output is produced within acceptable time.

We investigate compositional bounding of transition system diameters, with application in bounding the lengths of plans. We establish usefully-tight bounds by exploiting acyclicity in state-spaces. We provide mechanised proofs in HOL4 of the validity of our approach. Evaluating our bounds in a range of benchmarks, we demonstrate exponentially tighter upper bounds compared to existing methods. Treating both solvable and unsolvable benchmark problems, we also demonstrate the utility of our bounds in boosting planner performance. We enhance an existing planning procedure to use our bounds, and demonstrate significant coverage improvements, both compared to the base planner, and also in comparisons with state-of-the-art systems.

The times sure are a-changing. E3's always been known as a console-centric gaming show, and it definitely still is on the surface. Given the infiltration of AMD's APUs into the Xbox One and PlayStation 4, and the resurgence of PC gaming, plus Microsoft's ambitious Xbox Play Anywhere program, most of the blockbuster games announced for consoles at E3 actually wind up coming to PCs, too. We've sifted through all the new games at the E3 events from EA, Microsoft, Bethesda, Ubisoft, Sony, and The PC Gaming Show to find all the PC gems hidden among the console rubble. These are the E3 reveals that PC gamers need to know about. Wolfenstein: The New Order is one of the best single-player shooters of the past decade, and now B.J. Blazkowicz is back for more ludicrous-yet-heartfelt Nazi-stomping action.

I haven't said much about Workey for a few months. It has raised another $8 million and is opening up a New York office, focusing on NY as well as on San Francisco. The Israeli company says it worked with Amazon, Dell EMC, Oracle, and Yahoo during its Beta. Among Workey's features is one called social power: "Workey will promote your anonymous profile based on your connections, and suggest which friends can vouch for you for each opportunity." I monkeyed around with Workey a bit, and one interesting feature is that next to job listings, it pops up little notes indicating you're reasonably qualified, like "your proven record on Twitter puts you ahead of the pack for this opportunity."