More Like this

1. Auto-Differentiation of Relational Computations for Very Large Scale Machine Learning

   Yuxin Tang, Zhimin Ding (December 2023, Proceedings of Machine Learning Research)

   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. Meta Learning with Relational Information for Short Sequences

   Xie, Y; Jiang, H; Liu, F; Zhao, T; Zha, H (January 2019, Advances in neural information processing systems)

   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. Meta Learning with Relational Information for Short Sequences

   Xie, Yujia; Jiang, Haoming; Liu, Feng; Zhao, Tuo; Zha, Hongyuan Zha. (December 2019, Advances in neural information processing systems)

   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 Models from Relational Databases

   https://doi.org/10.48786/edbt.2024.61  

   Zhou, Lixi; Lin, Qi; Chowdhury, Kanchan; Masood, Saif; Eichenberger, Alexandre; Min, Hong; Sim, Alexander; Wang, Jie; Wang, Yida; Wu, Kesheng; et al (January 2024, OpenProceedings.org)

   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. Motivating relational organizing behavior for biodiversity conservation

   https://doi.org/10.1111/csp2.12880  

   Jones, Megan_S; Niemiec, Rebecca_M (January 2023, Conservation Science and Practice)

   Abstract As biodiversity loss and climate change accelerate, more people worldwide are engaging in conservation behaviors to “do their part.” Yet, individual behavior change alone is insufficient for the large‐scale, rapid change needed to address these crises. Relational organizing, which involves individuals reaching out to others in their social network, can enhance the speed and scale of conservation behavior change and address the complex, collective action nature of many conservation problems. However, many people practicing conservation behaviors in their own lives do not engage in relational organizing about conservation issues. Here, we suggest this may be the result of specific social‐psychological factors inhibiting people from reaching out to others. We summarize the evidence and offer a research and practice agenda to prioritize (1) understanding the social‐psychological barriers that prevent relational organizing, and (2) addressing these barriers through targeted outreach interventions to help scale and accelerate community action for conservation. 

   more » « less