Froid

Ramachandra, Karthik; Park, Kwanghyun; Emani, K. Venkatesh; Halverson, Alan; Galindo-Legaria, César A.; Cunningham, Conor

doi:10.1145/3186728.3164140

Cited by 39 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first technique is to prune the decision tree based on the selection queries. The second technique is to inline single and simple decision trees into UDFs leveraging the Froid framework [49]. However, Raven executes ensemble tree inferences (e.g., random forest) in ONNX runtime.…”

Section: Related Workmentioning

confidence: 99%

A Comparison of Decision Forest Inference Platforms from A Database Perspective

Guan¹,

Dwarampudi²,

Gunda³

et al. 2023

Preprint

View full text Add to dashboard Cite

Decision forest, including RandomForest, XGBoost, and LightGBM, is one of the most popular machine learning techniques used in many industrial scenarios, such as credit card fraud detection, ranking, and business intelligence. Because the inference process is usually performance-critical, a number of frameworks were developed and dedicated for decision forest inference, such as ONNX, TreeLite from Amazon, TensorFlow Decision Forest from Google, HummingBird from Microsoft, Nvidia FIL, and lleaves. However, these frameworks are all decoupled with data management frameworks. It is unclear whether in-database inference will improve the overall performance. In addition, these frameworks used different algorithms, optimization techniques, and parallelism models. It is unclear how these implementations will affect the overall performance and how to make design decisions for an in-database inference framework. In this work, we investigated the above questions by comprehensively comparing the end-to-end performance of the aforementioned inference frameworks and netsDB, an in-database inference framework we implemented. Through this study, we identified that netsDB is best suited for handling small-scale models on large-scale datasets and all-scale models on small-scale datasets, for which it achieved up to hundreds of times of speedup. In addition, the relation-centric representation we proposed significantly improved netsDB's performance in handling large-scale models, while the model reuse optimization we proposed further improved netsDB's performance in handling small-scale datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

A Comparison of Decision Forest Inference Platforms from A Database Perspective

Guan¹,

Dwarampudi²,

Gunda³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…While extending consumer database runtimes for properly supporting ML will bring the best performance, this is a herculean task because it requires the modification of decades-old systems. Conversely, the UDA/UDF approach is more generic, but it introduces nontrivial overheads [43], while limiting the set of possible crossoptimization between ML and relational algebra [44], [45]. Finally, factorized approaches (e.g., [46]) rewrite ML models in a database-friendly way.…”

Section: Related Workmentioning

confidence: 99%

Pushing ML Predictions Into DBMSs

Paganelli

Sottovia

Park

et al. 2023

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

In the past decade, many approaches have been suggested to execute ML workloads on a DBMS. However, most of them have looked at in-DBMS ML from a training perspective, whereas ML inference has been largely overlooked. We think that this is an important gap to fill for two main reasons: (1) in the near future, every application will be infused with some sort of ML capability; (2) behind every web page, application, and enterprise there is a DBMS, whereby in-DBMS inference is an appealing solution both for efficiency (e.g., less data movement), performance (e.g., cross-optimizations between relational operators and ML) and governance. In this paper, we study whether DBMSs are a good fit for prediction serving. We introduce a technique for translating trained ML pipelines containing both featurizers (e.g., one-hot encoding) and models (e.g., linear and tree-based models) into SQL queries, and we compare in-DBMS performance against popular ML frameworks such as Sklearn and ML.NET. Our experiments show that, when pushed inside a DBMS, trained ML pipelines can have performance comparable to ML frameworks in several scenarios, while they perform quite poorly on text featurization and over (even simple) neural networks.

show abstract

“…First, we assume that predictive pipelines are "pure", i.e., they do not contain arbitrary user-defined operators. There has been recent work [236] on compiling imperative UDFs (user-defined functions) into relational algebra, and we plan to make use of such techniques in HUMMINGBIRD in the future. Second, we do not support sparse data well.…”

Section: Assumptions and Limitationsmentioning

confidence: 99%