Summary of Ebes: Easy Benchmarking For Event Sequences, by Dmitry Osin et al.
EBES: Easy Benchmarking for Event Sequences
by Dmitry Osin, Igor Udovichenko, Viktor Moskvoretskii, Egor Shvetsov, Evgeny Burnaev
First submitted to arxiv on: 4 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents a comprehensive benchmark for Event Sequence (EvS) classification, a crucial task in various real-life applications such as healthcare, finance, and user interaction. The lack of standardization in current benchmarks hinders progress in the field, leading to unreliable conclusions and making it difficult to compare results across studies. To address this gap, the authors introduce EBES, a PyTorch library that implements 9 modern models, along with standardized evaluation scenarios and protocols. The benchmark features the largest collection of EvS datasets, including a novel synthetic dataset and real-world data from the largest publicly available banking dataset. The paper highlights the unique properties of EvS compared to other sequential data types, provides a performance ranking of modern models, and reveals the challenges associated with robust EvS learning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a benchmark for classifying event sequences in different fields like healthcare, finance, and user interaction. Event sequences are special kinds of data that have irregular time intervals and mix of numbers and categories. The current way of evaluating these sequences is not standardized, which makes it hard to compare results from different studies. To fix this, the authors made a library called EBES that has 9 modern models, ways to evaluate them, and a big collection of datasets for testing. They also found that some models do better than others in classifying event sequences, especially those using GRU-based models. |
Keywords
* Artificial intelligence * Classification
