We consider federated learning in tiered communication networks. Our network model consists of a set silos, each holding vertical partition the data. Each silo contains hub and clients, with silo’s data shard partitioned horizontally across its clients. propose Tiered Decentralized Coordinate Descent (TDCD), communication-efficient decentralized training algorithm for such two-tiered The client...

BACKGROUND The heads of the Global Fund and the GAVI Alliance have recently promoted the idea of an international tiered pricing framework for medicines, despite objections from civil society groups who fear that this would reduce the leeway for compulsory licenses and generic competition. This paper explores the extent to which an international tiered pricing framework and the present leeway f...

Data sparseness in tagging highly inflectional languages with large tagsets and scarce training resources is a problem that cannot be addressed using only common tagging techniques. Tiered tagging is a two-stage technique that uses for tagging a smaller ”hidden” tagset and, in the second phase, recovers the original tagset using a lexicon and a set of hand-written rules. The recovering is possi...

In this paper we describe a new baseline tagset induction algorithm, which unlike the one described in previous work is fully automatic and produces tagsets with better performance than before. The algorithm is an information lossless transformation of the MULTEXTEAST compliant lexical tags into a reduced tagset that can be mapped back on the lexicon tagset fully deterministic. From the baselin...

Abstract English as a medium of instruction (EMI) is commonly adopted strategy for higher education internationalisation. While there are numerous studies on the teaching practices EMI programmes, relationship between and structural inequalities has been less investigated, especially in “universal” systems. To address research gap, this study investigates two Taiwanese institutions (HEIs) under...