Related papers: Deep Data Flow Analysis
The capability of making interpretable and self-explanatory decisions is essential for developing responsible machine learning systems. In this work, we study the learning to explain problem in the scope of inductive logic programming…
Deep neural networks (DNNs) are of critical use in different domains. To accelerate DNN computation, tensor compilers are proposed to generate efficient code on different domain-specific accelerators. Existing tensor compilers mainly focus…
Background. Due to the widespread adoption of Artificial Intelligence (AI) and Machine Learning (ML) for building software applications, companies are struggling to recruit employees with a deep understanding of such technologies. In this…
The integration of Large Language Models (LLMs) with Graph Representation Learning (GRL) marks a significant evolution in analyzing complex data structures. This collaboration harnesses the sophisticated linguistic capabilities of LLMs to…
A typical compiler flow relies on a uni-directional sequence of translation/optimization steps that lower the program abstract representation, making it hard to preserve higher-level program information across each transformation step. On…
Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constrained environments. While modern frameworks incorporate various memory-saving techniques, they…
Structured LLM workflows, where specialized LLM sub-agents execute according to a predefined graph, have become a powerful abstraction for solving complex tasks. Optimizing such workflows, i.e., selecting configurations for each sub-agent…
We establish a translation between a formalism for dynamic programming over hypergraphs and the computation of semiring-based provenance for Datalog programs. The benefit of this translation is a new method for computing provenance for a…
Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs. In this paper, we present the design principles and implementation of Deep Graph Library (DGL). DGL distills the…
We present sql4ml, a system for expressing supervised machine learning (ML) models in SQL and automatically training them in TensorFlow. The primary motivation for this work stems from the observation that in many data science tasks there…
Datacenters are increasingly becoming heterogeneous, and are starting to include specialized hardware for networking, video processing, and especially deep learning. To leverage the heterogeneous compute capability of modern datacenters, we…
Automatic machine learning (AutoML) is an area of research aimed at automating machine learning (ML) activities that currently require human experts. One of the most challenging tasks in this field is the automatic generation of end-to-end…
Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code that supports symbolic, graph-based Deep…
With the emerging trend of GPT models, we have established a framework called AutoML-GPT that integrates a comprehensive set of tools and libraries. This framework grants users access to a wide range of data preprocessing techniques,…
Automated log analysis is crucial in modern software-intensive systems for facilitating program comprehension throughout software maintenance and engineering life cycles. Existing methods perform tasks such as log parsing and log anomaly…
Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute. However, as frameworks specialize performance optimization to patterns in popular networks, they…
Despite the remarkable progress of large language models (LLMs), the capabilities of standalone LLMs have begun to plateau when tackling real-world, complex tasks that require interaction with external tools and dynamic environments.…
Data pipelines are essential in stream processing as they enable the efficient collection, processing, and delivery of real-time data, supporting rapid data analysis. In this paper, we present AutoStreamPipe, a novel framework that employs…
Large language models (LLMs) have achieved remarkable performance in various evaluation benchmarks. However, concerns are raised about potential data contamination in their considerable volume of training corpus. Moreover, the static nature…
A key feature of inductive logic programming (ILP) is its ability to learn first-order programs, which are intrinsically more expressive than propositional programs. In this paper, we introduce techniques to learn higher-order programs.…