skip to main content


This content will become publicly available on July 29, 2024

Title: Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning
The relational data model was designed to facilitate large-scale data management and analytics. We consider the problem of how to differentiate computations expressed relationally. We show experimentally that a relational engine running an auto-differentiated relational algorithm can easily scale to very large datasets, and is competitive with state-of-the-art, special-purpose systems for large-scale distributed machine learning.  more » « less
Award ID(s):
2008240
NSF-PAR ID:
10477650
Author(s) / Creator(s):
; ; ; ; ;
Publisher / Repository:
PMLR (ICML)
Date Published:
Journal Name:
Proceedings of Machine Learning Research (ICML)
Volume:
202
ISSN:
2640-3498
Page Range / eLocation ID:
33581--33598
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. The relational data model was designed to facilitate large-scale data management and analytics. We consider the problem of how to differentiate computations expressed relationally. We show experimentally that a relational engine running an auto-differentiated relational algorithm can easily scale to very large datasets, and is competitive with state-of-the-art, special-purpose systems for large-scale distributed machine learning. 
    more » « less
  2. This paper proposes a new meta-learning method – named HARMLESS (HAwkes Relational Meta LEarning method for Short Sequences) for learning heterogeneous point process models from short event sequence data along with a relational network. Specifically, we propose a hierarchical Bayesian mixture Hawkes process model, which naturally incorporates the relational information among sequences into point process modeling. Compared with existing methods, our model can capture the underlying mixed-community patterns of the relational network, which simultaneously encourages knowledge sharing among sequences and facilitates adaptive learning for each individual sequence. We further propose an efficient stochastic variational meta expectation maximization algorithm that can scale to large problems. Numerical experiments on both synthetic and real data show that HARMLESS outperforms existing methods in terms of predicting the future events. 
    more » « less
  3. This paper proposes a new meta-learning method – named HARMLESS (HAwkes Relational Meta LEarning method for Short Sequences) for learning heterogeneous point process models from short event sequence data along with a relational net- work. Specifically, we propose a hierarchical Bayesian mixture Hawkes process model, which naturally incorporates the relational information among sequences into point process modeling. Compared with existing methods, our model can capture the underlying mixed-community patterns of the relational network, which simultaneously encourages knowledge sharing among sequences and facilitates adaptive learning for each individual sequence. We further propose an efficient stochastic variational meta expectation maximization algorithm that can scale to large problems. Numerical experiments on both synthetic and real data show that HARMLESS outperforms existing methods in terms of predicting the future events. 
    more » « less
  4. Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains, sparking growing interest recently. In this visionary paper, we embark on a comprehensive exploration of representative architectures to address the requirement. We highlight three pivotal paradigms: The state-of-the-art \textit{DL-centric} architecture offloads DL computations to dedicated DL frameworks. The potential \textit{UDF-centric} architecture encapsulates one or more tensor computations into User Defined Functions (UDFs) within the relational database management system (RDBMS). The potential \textit{relation-centric} architecture aims to represent a large-scale tensor computation through relational operators. While each of these architectures demonstrates promise in specific use scenarios, we identify urgent requirements for seamless integration of these architectures and the middle ground in-between these architectures. We delve into the gaps that impede the integration and explore innovative strategies to close them. We present a pathway to establish a novel RDBMS for enabling a broad class of data-intensive DL inference applications. 
    more » « less
  5. What can we learn about the functional organization of cortical microcircuits from large-scale recordings of neural activity? To obtain an explicit and interpretable model of time-dependent functional connections between neurons and to establish the dynamics of the cortical information flow, we develop ‘dynamic neural relational inference’ (dNRI). We study both synthetic and real-world neural spiking data and demonstrate that the developed method is able to uncover the dynamic relations between neurons more reliably than existing baselines. 
    more » « less