Compilation Techniques for Incremental Collection Processing

Many map-reduce frameworks as well as NoSQL systems rely on collection programming as their interface of choice due to its rich semantics along with an easily parallelizable set of primitives. Unfortunately, the potential of collection programming is not entirely fulfilled by current systems as they lack efficient incremental view maintenance (IVM) techniques for queries producing large nested results. This comes as a consequence of the fact that the nesting of collections does not enjoy the same algebraic properties underscoring the optimization potential of typical collection processing constructs. We propose the first solution for the efficient incrementalization of collection programming in terms of its core constructs as captured by the positive nested relational calculus (NRC+) on bags (with integer multiplicities). We take an approach based on delta query derivation, whose goal is to generate delta queries which, given a small change in the input, can update the materialized view more efficiently than via recomputation. More precisely, we model the cost of NRC+ operators and classify queries as efficiently incrementalizable if their delta has a strictly lower cost than full re-evaluation. Then, we identify IncNRC+, a large fragment of NRC+ that is efficiently incrementalizable and we provide a semantics-preserving translation that takes any NRC+ query to a collection of IncNRC+ queries. Furthermore, we prove that incrementalmaintenance for NRC+ is within the complexity class NC0 and we showcase how Recursive IVM, a technique that has provided significant speedups over traditional IVM in the case of flat queries, can also be applied to IncNRC+ . Existing systems are also limited wrt. the size of inner collections that they can effectively handle before running into severe performance bottlenecks. In particular, in the face of nested collections with skewed cardinalities developers typically have to undergo a painful process of manual query re-writes in order to ensure that the largest inner collections in their workloads are not impacted by these limitations. To address these issues we developed SLeNDer, a compilation framework that given a nested query generates a set of semantically equivalent (partially) shredded queries that can be efficiently evaluated and incrementalized using state of the art techniques for handling skew and applying delta changes, respectively. The derived queries expose nested collections to the same opportunities for distributing their processing and incrementally updating their contents as those enjoyed by top-level collections, leading on our benchmark to up to 16.8x and 21.9x speedups in terms of offline and online processing, respectively. In order to enable efficient IVM for the increasingly common case of collection programming with functional values as in Links, we also discuss the efficient incrementalization of simplytyped lambda calculi, under the constraint that their primitives are themselves efficiently incrementalizable.

Incremental View Maintenance for Collection Programming

Christoph Koch, Daniel Lupei, Val Tannen

In the context of incremental view maintenance (IVM), delta query derivation is an essential technique for speeding up the processing of large, dynamic datasets. The goal is to generate delta queries that, given a small change in the input, can update the materialized view more efficiently than via recomputation. In this work we propose the first solution for the efficient incrementalization of positive nested relational calculus (NRC+) on bags (with integer multiplicities). More precisely, we model the cost of NRC+ operators and classify queries as efficiently incrementalizable if their delta has a strictly lower cost than full re-evaluation. Then, we identify NRC+, a large fragment of NRC+ that is efficiently incrementalizable and we provide a semantics-preserving translation that takes any NRC+ query to a collection of IncNRC+ queries. Furthermore, we prove that incremental maintenance for NRC+ is within the complexity class NC0 and we showcase how recursive IVM, a technique that has provided significant speedups over traditional IVM in the case of flat queries, can also be applied to IncNRC+.

ACM2016

Efficient Online Processing for Advanced Analytics

Mohamed Elsayed Mohamed Ahmed El Seidy

With the advent of emerging technologies and the Internet of Things, the importance of online data analytics has become more pronounced. Businesses and companies are adopting approaches that provide responsive analytics to stay competitive in the global marketplace. Online analytics allow data analysts to promptly react to patterns or to gain preliminary insights from early results that aid in research, decision making, and effective strategy planning. The growth of data-velocity in a variety of domains including, high-frequency trading, social networks, infrastructure monitoring, and advertising require adopting online engines that can efficiently process continuous streams of data. This thesis presents foundations, techniques, and systems' design that extend the state-of-the-art in online query processing to efficiently support relational joins with arbitrary join-predicates (beyond traditional equi-joins); and to support other data models (beyond relational) that target machine learning and graph computations. The thesis is divided into two parts: We first present a brief overview of Squall, our open-source online query processing engine that supports SQL-like queries on top of streams. Then, we focus on extending Squall to support efficient theta-join processing. Scalable distributed join processing requires a partitioning policy that evenly distributes the processing load while minimizing the size of maintained state and duplicated messages. Efficient load-balance demands apriori-statistics which are not available in the online setting. We propose a novel operator that continuously adjusts itself to the data dynamics, through adaptive dataflow routing and state repartitioning. It is also resilient to data-skew, maintains high throughput rates, avoids blocking during state repartitioning, and behaves as a black-box dataflow operator with provable performance guarantees. Our evaluation demonstrates that the proposed operator outperforms the state-of-the-art static partitioning schemes in resource utilization, throughput, and execution time up to 7x. In the second part, we present a novel framework that supports the Incremental View Maintenance (IVM) of workloads expressed as linear algebra programs. Linear algebra represents a concrete substrate for advanced analytical tasks including, machine learning, scientific computation, and graph algorithms. Previous works on relational calculus IVM are not applicable to matrix algebra workloads. This is because a single entry change to an input-matrix results in changes all over the intermediate views, rendering IVM useless in comparison to re-evaluation. We present Lago, a unified modular compiler framework that supports the IVM of a broad class of linear algebra programs. Lago automatically derives and optimizes incremental trigger programs of analytical computations, while freeing the user from erroneous manual derivations, low-level implementation details, and performance tuning. We present a novel technique that captures

\Delta

changes as low-rank matrices. Low-rank matrices are representable in a compressed factored form that enables cheaper computations. Lago automatically propagates the factored representation across program statements to derive an efficient trigger program. Moreover, Lago extends its support to other domains that use different semi-ring configurations, e.g., graph applications. Our evaluation results demonstrate orders of magnitude (10x-10

EPFL2017

Graph Signal Processing

Ntorina Thanou

Over the past few decades we have been experiencing an explosion of information generated by large networks of sensors and other data sources. Much of this data is intrinsically structured, such as traffic evolution in a transportation network, temperature values in different geographical locations, information diffusion in social networks, functional activities in the brain, or 3D meshes in computer graphics. The representation, analysis, and compression of such data is a challenging task and requires the development of new tools that can identify and properly exploit the data structure. In this thesis, we formulate the processing and analysis of structured data using the emerging framework of graph signal processing. Graphs are generic data representation forms, suitable for modeling the geometric structure of signals that live on topologically complicated domains. The vertices of the graph represent the discrete data domain, and the edge weights capture the pairwise relationships between the vertices. A graph signal is then defined as a function that assigns a real value to each vertex. Graph signal processing is a useful framework for handling efficiently such data as it takes into consideration both the signal and the graph structure. In this work, we develop new methods and study several important problems related to the representation and structure-aware processing of graph signals in both centralized and distributed settings. We focus in particular in the theory of sparse graph signal representation and its applications and we bring some insights towards better understanding the interplay between graphs and signals on graphs. First, we study a novel yet natural application of the graph signal processing framework for the representation of 3D point cloud sequences. We exploit graph-based transform signal representations for addressing the challenging problem of compression of data that is characterized by dynamic 3D positions and color attributes. Next, we depart from graph-based transform signal representations to design new overcomplete representations, or dictionaries, which are adapted to specific classes of graph signals. In particular, we address the problem of sparse representation of graph signals residing on weighted graphs by learning graph structured dictionaries that incorporate the intrinsic geometric structure of the irregular data domain and are adapted to the characteristics of the signals. Then, we move to the efficient processing of graph signals in distributed scenarios, such as sensor or camera networks, which brings important constraints in terms of communication and computation in realistic settings. In particular, we study the effect of quantization in the distributed processing of graph signals that are represented by graph spectral dictionaries and we show that the impact of the quantization depends on the graph geometry and on the structure of the spectral dictionaries. Finally, we focus on a widely used graph process, the problem of distributed average consensus in a sensor network where sensors exchange quantized information with their neighbors. We propose a novel quantization scheme that depends on the graph topology and exploits the increasing correlation between the values exchanged by the sensors throughout the iterations of the consensus algorithm.

EPFL2016