ESI Group (Sweden)

The standard evaluation protocol for measuring the quality of Knowledge Graph Completion methods - the task of inferring new links to be added to a graph - typically involves a step which ranks every entity of a Knowledge Graph to assess their fit as a head or tail of a candidate link to be added. In Knowledge Graphs on a larger scale, this task rapidly becomes prohibitively heavy. Previous approaches mitigate this problem by using random sampling of entities to assess the quality of links predicted or suggested by a method. However, we show that this approach has serious limitations since the ranking metrics produced do not properly reflect true outcomes. In this paper, we present a thorough analysis of these effects along with the following findings. First, we empirically find and theoretically motivate why sampling uniformly at random vastly overestimates the ranking performance of a method. We show that this can be attributed to the effect of easy versus hard negatives. Second, we propose a framework that uses relational recommenders to guide the selection of candidates for evaluation. We provide both theoretical and empirical justification of our methodology, and find that simple and fast methods work extremely well, matching advanced neural approaches. Even when a large portion of the true candidates for a property are missed, the estimation of the ranking metrics on a downstream model barely deteriorates. With our proposed framework, we can reduce the time and computation needed similar to random sampling strategies while vastly improving the estimation; on ogbl-wikikg2, we show that accurate estimations of the full ranking can be obtained in 20 seconds instead of 30 minutes. We conclude that considerable computational effort can be saved by effective preprocessing and sampling methods and still reliably predict performance accurately of the true performance for the entire ranking procedure. We make our code available to the community<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup><sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>Accessible at https://github.com/Filco306/are-we-wasting-time.

This one-day hybrid workshop builds on previous feminist CSCW workshops to explore feminist theoretical and methodological approaches that have provided us with useful tools to see things differently and make space for change. Since its inception over a decade ago, feminist HCI has progressed from the margins to mainstream HCI, with numerous references in the literature. Feminist HCI has also evolved to incorporate other critical HCI practices such as Queer HCI, participatory design, and speculative design. While feminist approaches have grown in popularity and become mainstream, it is getting more difficult to distinguish the feminist emancipatory core from other attempts of developing and improving society in various ways. In this workshop, we therefore want to revisit our feminist roots, where theory is a liberatory and creative practice, motivated by affect, curiosity, and wonder. From this standpoint, we consider which of our feminist tools can make a significant difference today, in a highly datafied world. The goal of this workshop is to; 1) create an inventory of feminist theories and concepts that have had an impact on our work as designers, educators, researchers, and activists; 2) develop a feminist toolbox for the CSCW community to strengthen our feminist literacy.

Federated machine learning promises to overcome the input privacy challenge in machine learning. By iteratively updating a model on private clients and aggregating these local model updates into a global federated model, private data is incorporated in the federated model without needing to share and expose that data. Several open software projects for federated learning have appeared. Most of them focuses on supporting flexible experimentation with different model aggregation schemes and with different privacy-enhancing technologies. However, there is a lack of open frameworks that focuses on critical distributed computing aspects of the problem such as scalability and resilience. It is a big step to take for a data scientist to go from an experimental sandbox to testing their federated schemes at scale in real-world geographically distributed settings. To bridge this gap we have designed and developed a production-grade hierarchical federated learning framework, FEDn. The framework is specifically designed to make it easy to go from local development in pseudo-distributed mode to horizontally scalable distributed deployments. FEDn both aims to be production grade for industrial applications and a flexible research tool to explore real-world performance of novel federated algorithms and the framework has been used in number of industrial and academic R&#x0026;D projects. In this paper we present the architecture and implementation of FEDn. We demonstrate the framework&#x0027;s scalability and efficiency in evaluations based on two case-studies representative for a cross-silo and a cross-device use-case respectively.

Size homogeneous heparin oligosaccharides were prepared from nitrous acid depolymerized heparin by means of repeated gel filtration chromatography. These oligosaccharides were then further separated with respect to affinity for antithrombin by means of affinity chromatography. All the high-affinity oligosaccharides thus obtained had a strong ability to potentiate factor Xa inhibition while their ability to inhibit factor IIa abruptly dropped below a chain length of 20 monosaccharides. In a rabbit stasis model, high-affinity oligosaccharides below a chain length of 20 units also showed a continuous decrease in antithrombotic effect with increasing degree of depolymerization. However, there was no distinct drop paralleling the thrombin inhibiting capacity. Low-affinity oligosaccharides also exhibited a weak antithrombotic effect, although they did not always contribute to an increased anti-factor Xa activity ex vivo. This was the case whether or not they were administered alone or in combination with high-affinity oligosaccharides. Low-affinity oligosaccharides may therefore exert an antithrombotic effect per se with a mechanism of action that is independent of antithrombin III.