Microorganisms such as bacteria perform critical functions in the soil ecosystem: they mediate essential carbon, nitrogen, and nutrient cycling processes in soils. To manage the health and functions of soils, it is important to understand which soil functions are related the most to which microbial taxa-but this taxon-to-function link is difficult to discover because of the size and complexity of the soil ecosystem. A feasible solution is to discover functional links at the level of groups instead of individuals, using observational data of both taxa abundance and soil function indicators. We thus aim to learn the functional co-response group: a group of taxa whose co-response effect (the representative characteristic of the whole functional group) co-responds (associates well statistically) to a functional variable. Unlike the existing method, we model the soil microbial community as an ecological co-occurrence network with the taxa as nodes (weighted by their abundance) and their relationships (a combination from both spatial and functional ecological aspects) as edges (weighted by the strength of the relationships). Then, we design a method called gFlora which notably uses graph convolution over this co-occurrence network to compute the co-response effect of the group, such that the network topology is also considered in the discovery process. We evaluate gFlora on four real-world soil microbiome datasets (bacteria and nematodes combined with two soil functions: nitrogen mineralization and crop yield). gFlora outperforms the competing method on all evaluation metrics, and it discovers new functional evidence for taxa which were so far under-studied. We show that the graph convolution is crucial to taxa with relatively low abundance (thus removing the bias towards taxa with higher abundance), and the discovered bacteria of different genera are distributed in the co-occurrence network but remain tightly connected among themselves, demonstrating that topologically they fill different but collaborative functional roles in the ecological community.

Small and medium enterprises rely on detailed Web analytics to be informed about their market and competition. Focused crawlers meet this demand by crawling and indexing specific parts of the Web. Critically, a focused crawler must quickly find new pages that have not yet been indexed. Since a new page can be discovered only by following a new outlink, predicting new outlinks is very relevant in practice. In the literature, many feature designs have been proposed for predicting changes in the Web. In this work we provide a structured analysis of this problem, using new outlinks as our running prediction target. Specifically, we unify earlier feature designs in a taxonomic arrangement of features along two dimensions: static versus dynamic features, and features of a page versus features of the network around it. Within this taxonomy, complemented by our new (mainly, dynamic network) features, we identify best predictors for new outlinks. Our main conclusion is that most informative features are the recent history of new outlinks on a page itself, and of its content-related pages. Hence, we propose a new ‘look back, look around’ (LBLA) model, that uses only these features. With the obtained predictions, we design a number of scoring functions to guide a focused crawler to pages with most new outlinks, and compare their performance. The LBLA approach proved extremely effective, outperforming other models including those that use a most complete set of features. One of the learners we use, is the recent NGBoost method that assumes a Poisson distribution for the number of new outlinks on a page, and learns its parameters. This connects the two so far unrelated avenues in the literature: predictions based on features of a page, and those based on probabilistic modeling. All experiments were carried out on an original dataset, made available by a commercial focused crawler.

Finding the most influential nodes in a network is a computationally hard problem with several possible applications in various kinds of network-based problems. While several methods have been proposed for tackling the influence maximisation (IM) problem, their runtime typically scales poorly when the network size increases. Here, we propose an original method, based on network downscaling, that allows a multi-objective evolutionary algorithm (MOEA) to solve the IM problem on a reduced scale network, while preserving the relevant properties of the original network. The downscaled solution is then upscaled to the original network, using a mechanism based on centrality metrics such as PageRank. Our results on eight large networks (including two with $\sim$50k nodes) demonstrate the effectiveness of the proposed method with a more than 10-fold runtime gain compared to the time needed on the original network, and an up to $82\%$ time reduction compared to CELF.

Humans are good at compositional zero-shot reasoning; someone who has never seen a zebra before could nevertheless recognize one when we tell them it looks like a horse with black and white stripes. Machine learning systems, on the other hand, usually leverage spurious correlations in the training data, and while such correlations can help recognize objects in context, they hurt generalization. To be able to deal with underspecified datasets while still leveraging contextual clues during classification, we propose ProtoProp, a novel prototype propagation graph method. First we learn prototypical representations of objects (e.g., zebra) that are independent w.r.t. their attribute labels (e.g., stripes) and vice versa. Next we propagate the independent prototypes through a compositional graph, to learn compositional prototypes of novel attribute-object combinations that reflect the dependencies of the target distribution. The method does not rely on any external data, such as class hierarchy graphs or pretrained word embeddings. We evaluate our approach on AO-Clevr, a synthetic and strongly visual dataset with clean labels, UT-Zappos, a noisy real-world dataset of fine-grained shoe types, and C-GQA, a large-scale object detection dataset modified for compositional zero-shot learning. We show that in the generalized compositional zero-shot setting we outperform state-of-the-art results, and through ablations we show the importance of each part of the method and their contribution to the final results. The code is available on github.

Identifying important nodes for disease spreading is a central topic in network epidemiology. We investigate how well the position of a node, characterized by standard network measures, can predict its epidemiological importance in any graph of a given number of nodes. This is in contrast to other studies that deal with the easier prediction problem of ranking nodes by their epidemic importance in given graphs. As a benchmark for epidemic importance, we calculate the exact expected outbreak size given a node as the source. We study exhaustively all graphs of a given size, so do not restrict ourselves to certain generative models for graphs, nor to graph data sets. Due to the large number of possible nonisomorphic graphs of a fixed size, we are limited to ten-node graphs. We find that combinations of two or more centralities are predictive (R2 scores of 0.91 or higher) even for the most difficult parameter values of the epidemic simulation. Typically, these successful combinations include one normalized spectral centrality (such as PageRank or Katz centrality) and one measure that is sensitive to the number of edges in the graph.

De novo genome assemblers designed for short k-mer length or using short raw reads are unlikely to recover complex features of the underlying genome, such as repeats hundreds of bases long. We implement a stochastic machine-learning method which obtains accurate assemblies with repeats and self-validates assemblies via consensus. For this, a prior assembler is extended with the ability to (a) assemble variable-length raw reads, which may span and unambiguously recover interspersed repeats in the genome, and (b) recognize long, direct terminal repeats during the assembly, then report an unambiguous circular assembly. Consensus is obtained via stochastically independent runs of the assembler on the same read library. We experiment on viral and mitochondrial genomes of up to 41 kbp, with synthetic raw-read libraries, to be able to evaluate the assembly against a reference. We show the prerequisites for obtaining accurate assemblies. For genomes with interspersed repeats, using raw reads of average length comparable to the repeat length likely gives an accurate genome. Genomes with long direct terminal repeats can be assembled accurately also with reads shorter than the repeat length. In both cases, a simple majority forms consensus, since over 70 % of independent runs on this set of genomes yield a correct assembly.

Wireless sensor network (WSN) routing protocols, e.g., the Collection Tree Protocol (CTP), are designed to adapt in an ad-hoc fashion to the quality of the environment. WSNs thus have high internal dynamics and complex global behavior. Classical techniques for performance evaluation (such as testing or verification) fail to uncover the cases of extreme behavior which are most interesting to designers. We contribute a practical framework for performance evaluation of WSN protocols. The framework is based on multi-objective optimization, coupled with protocol simulation and evaluation of performance factors. For evaluation, we consider the two crucial functional and non-functional performance factors of a WSN, respectively: the ratio of data delivery from the network (DDR), and the total energy expenditure of the network (COST). We are able to discover network topological configurations over which CTP has unexpectedly low DDR and/or high COST performance, and expose full Pareto fronts which show what the possible performance tradeoffs for CTP are in terms of these two performance factors. Eventually, Pareto fronts allow us to bound the state space of the WSN, a fact which provides essential knowledge to WSN protocol designers.

We describe the first software tool for the verification of TinyOS 2, MSP430 applications at compile-time. Given assertions upon the state of the sensor node, the tool boundedly explores all program executions and returns to the programmer an error trace leading to any assertion violation. Besides memory-related errors (out-of-bounds arrays, nullpointer dereferences), we verify application-specific assertions, including low-level assertions upon the state of the registers and peripherals.