Research

You can use our plugin to insert parts from your activity report (raweb)service.

Presentation

Example : tyrex

Overall objectives

Objectives

We develop the foundations for the next generation of information extraction, data analysis and neuro-symbolic programming systems. Our research extends ideas from data management, artificial intelligence, programming languages and logic.

Extracting value from data increasingly requires sophisticated algorithms to represent, query, process, analyze and interpret data. We develop the foundations of data processing systems and neuro-symbolic programming, with a focus on extracting information from graph structures. These graph structures are obtained from raw data that may be more or less structured, noisy, uncertain or incomplete. Challenges include robust, efficient and scalable processing of large graphs obtained from such data. We study and build new information extraction methods, as well as new robust and scalable programming methods for rich graph data structures.

Last activity report : 2023

Results

New results

Knowledge Enhanced Graph Neural Networks for Graph Completion

Graph data is omnipresent and has a wide variety of applications, such as in natural science, social networks, or the semantic web. However, while being rich in information, graphs are often noisy and incomplete. As a result, graph completion tasks, such as node classification or link prediction, have gained attention. On the one hand, neural methods, such as graph neural networks, have proven to be robust tools for learning rich representations of noisy graphs. On the other hand, symbolic methods enable exact reasoning on graphs. We propose Knowledge Enhanced Graph Neural Networks (KeGNN), a neuro-symbolic framework for graph completion that combines both paradigms as it allows for the integration of prior knowledge into a graph neural network model. Essentially, KeGNN consists of a graph neural network as a base upon which knowledge enhancement layers are stacked with the goal of refining predictions with respect to prior knowledge. We instantiate KeGNN in conjunction with two state-of-the-art graph neural networks, Graph Convolutional Networks and Graph Attention Networks, and evaluate KeGNN on multiple benchmark datasets for node classification 2 [6.1.2].

Reproduce, Replicate, Reevaluate. The Long but Safe Way to Extend Machine Learning Methods

Reproducibility is a desirable property of scientific research. On the one hand, it increases confidence in results. On the other hand, reproducible results can be extended on a solid basis. In rapidly developing fields such as machine learning, the latter is particularly important to ensure the reliability of research. We present a systematic approach to reproducing (using the available implementation), replicating (using an alternative implementation) and reevaluating (using different datasets) state-of-the-art experiments. This approach enables the early detection and correction of deficiencies and thus the development of more robust and transparent machine learning methods. We detail the independent reproduction, replication, and reevaluation of initially published experiments with a method that we want to extend. For each step, we identify issues and draw lessons learned. We further discuss solutions that have proven effective in overcoming the encountered problems. This work can serve as a guide for further reproducibility studies and generally improve reproducibility in machine learning 3 [6.1.3].

Efficient Enumeration of Recursive Plans in Transformation-based Query Optimizers

Query optimizers built on the transformation-based Volcano/Cascades framework are used in many database systems. Transformations proposed earlier on the logical query dag (LQDAG) data structure, which is key in such a framework, focus only on recursion-free queries. We propose the recursive logical query dag (RLQDAG) which extends the LQDAG with the ability to capture and transform recursive queries, leveraging recent developments in recursive relational algebra. Specifically, this extension includes: (i) the ability of capturing and transforming sets of recursive relational terms thanks to (ii) annotated equivalence nodes used for guiding transformations that are more complex in the presence of recursion; and (iii) RLQDAG rewrite rules that transform sets of subterms in a grouped manner, instead of transforming individual terms in a sequential manner; and that (iv) incrementally update the necessary annotations. Core concepts of the RLQDAG are formalized using a syntax and formal semantics with a particular focus on subterm sharing and recursion. The result is a clean generalization of the LQDAG transformation-based approach, enabling more efficient explorations of plan spaces for recursive queries. An implementation of the proposed approach shows significant performance gains compared to the state-of-the-art 4, 6 [6.1.1].

The mu-RA System for Recursive Path Queries over Graphs

We demonstrate a system for recursive query answering over graphs. The system is based on a complete implementation of the recursive relational algebra mu-RA, extended with parsers and compilers adapted for queries over knowledge and property graphs. Each component of the system comes with novelty for processing recursion. As a result, one can formulate, optimize and efficiently answer expressive queries that navigate recursively along paths in different types of graphs. We demonstrate the system on real datasets and show how it performs considering other state-of-the-art systems 1 [6.1.1].

Efficient Iterative Programs with Distributed Data Collections

Big data programming frameworks have become increasingly important for the development of applications for which performance and scalability are critical. In those complex frameworks, optimizing code by hand is hard and time-consuming, making automated optimization particularly necessary. In order to automate optimization, a prerequisite is to find suitable abstractions to represent programs; for instance, algebras based on monads or monoids to represent distributed data collections. Currently, however, such algebras do not represent recursive programs in a way which allows for analyzing or rewriting them. In this paper, we extend a monoid algebra with a fixpoint operator for representing recursion as a first class citizen and show how it enables new optimizations. Experiments with the Spark platform illustrate performance gains brought by these systematic optimizations 5.

You can write want you want/need on this page by using HTML tags in the text editor or use the visual editor.

  • Research direction 1

    …….

  • Research direction 2

    ……….

  • Research direction 3

    ……….

    • Comments are closed.