Set Of Key-value Pairs Research Articles

On separating long- and short-term memories in hyperdimensional computing.

Operations on high-dimensional, fixed-width vectors can be used to distribute information from several vectors over a single vector of the same width. For example, a set of key-value pairs can be encoded into a single vector with multiplication and addition of the corresponding key and value vectors: the keys are bound to their values with component-wise multiplication, and the key-value pairs are combined into a single superposition vector with component-wise addition. The superposition vector is, thus, a memory which can then be queried for the value of any of the keys, but the result of the query is approximate. The exact vector is retrieved from a codebook (a.k.a. item memory), which contains vectors defined in the system. To perform these operations, the item memory vectors and the superposition vector must be the same width. Increasing the capacity of the memory requires increasing the width of the superposition and item memory vectors. In this article, we demonstrate that in a regime where many (e.g., 1,000 or more) key-value pairs are stored, an associative memory which maps key vectors to value vectors requires less memory and less computing to obtain the same reliability of storage as a superposition vector. These advantages are obtained because the number of storage locations in an associate memory can be increased without increasing the width of the vectors in the item memory. An associative memory would not replace a superposition vector as a medium of storage, but could augment it, because data recalled from an associative memory could be used in algorithms that use a superposition vector. This would be analogous to how human working memory (which stores about seven items) uses information recalled from long-term memory (which is much larger than the working memory). We demonstrate the advantages of an associative memory experimentally using the storage of large finite-state automata, which could model the storage and recall of state-dependent behavior by brains.

Raising the Parallel Abstraction Level for Streaming Analytics Applications

In the stream processing domain, applications are represented by graphs of operators arbitrarily connected and filled with their business logic code. The APIs of existing Stream Processing Systems (SPSs) ease the development of transformations that recur in the streaming practice (e.g., filtering, aggregation and joins). In contrast, their parallelism abstractions are quite limited since they provide support to stateless operators only, or when the state is organized in a set of key-value pairs. This paper presents how the parallel patterns methodology can be revisited for sliding-window streaming analytics. Our vision fosters a design process of the application as composition and nesting of ready-to-use patterns provided through a C++17 fluent interface. Our prototype implements the run-time system of the patterns in the FastFlow parallel library expressing thread-based parallelism. The experimental analysis shows interesting outcomes. First, our pattern-based approach allows easy prototyping of different versions of the application, and the programmer can leverage nesting of patterns to increase performance (up to 37% in one of the two considered test-bed cases). Second, our FastFlow implementation outperforms (three times faster) the handmade porting of our patterns in popular JVM-based SPSs. Finally, in the concluding part of this paper, we explore the use of a task-based run-time system, by deriving interesting insights into how to make our patterns library suitable for multi backends.

Finite-State Map-Reduce Computation and Relational Algebra Queries

We introduce three formal models of distributed systems for query evaluation on massive databases: Distributed Streaming with Register Automata (DSAs), Distributed Streaming with Register Transducers (DSTs), and Distributed Streaming with Register Transducers and Joins (DSTJs). These models are based on the map-reduce paradigm where the input is transformed into a dataset of key-value pairs, and on each key a local computation is performed on the values associated with that key resulting in another set of key-value pairs. Computation proceeds in a constant number of rounds, where the result of the last round is the input to the next round, and transformation of key-value pairs is required to be generic. The difference between the three models is in the local computation part. In DSAs it is limited to making one pass over its input using a register automaton, while in DSTs it can make two passes: in the first pass it uses a finite state automaton and in the second it uses a register transducer. The third model DSTJs is an extension of DSTs, where local computations are capable of constructing the Cartesian product of two sets. We obtain the following results: (1) DSAs can evaluate first-order queries over bounded degree databases; (2) DSTs can evaluate semijoin algebra queries over arbitrary databases; (3) DSTJs can evaluate the whole relational algebra over arbitrary databases; (4) DSTJs are strictly stronger than DSTs, which in turn are strictly stronger than DSAs; (5) within DSAs, DSTs, and DSTJs, there is a strict hierarchy w.r.t. the number of rounds.

External-Memory Multimaps

Many data structures support dictionaries, also known as maps or associative arrays, which store and manage a set of key-value pairs. A multimap is generalization that allows multiple values to be associated with the same key. For example, the inverted file data structure that is used prevalently in the infrastructure supporting search engines is a type of multimap, where words are used as keys and document pointers are used as values. We study the multimap abstract data type and how it can be implemented efficiently online in external memory frameworks, with constant expected I/O performance. The key technique used to achieve our results is a combination of cuckoo hashing using buckets that hold multiple items with a multiqueue implementation to cope with varying numbers of values per key. Our external-memory results are for the standard two-level memory model.

Simple and Efficient Model Filtering in Statistical Machine Translation

Simple and Efficient Model Filtering in Statistical Machine Translation Data availability and distributed computing techniques have allowed statistical machine translation (SMT) researchers to build larger models. However, decoders need to be able to retrieve information efficiently from these models to be able to translate an input sentence or a set of input sentences. We introduce an easy to implement and general purpose solution to tackle this problem: we store SMT models as a set of key-value pairs in an HFile. We apply this strategy to two specific tasks: test set hierarchical phrase-based rule filtering and n-gram count filtering for language model lattice rescoring. We compare our approach to alternative strategies and show that its trade offs in terms of speed, memory and simplicity are competitive.