# Embedding-Aware Feature Discovery: Bridging Latent Representations and Interpretable Features in Event Sequences

arXiv: https://arxiv.org/abs/2603.15713 · HTML: https://mlsanity.com/paper/2603.15713/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [Time2Vec: Learning a Vector Representation of Time](https://mlsanity.com/paper/1907.05321/) (2019)
- [On Embeddings for Numerical Features in Tabular Deep Learning](https://mlsanity.com/paper/2203.05556/) (2022)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning](https://mlsanity.com/paper/2402.17453/) (2024)
- [Tabular Transformers for Modeling Multivariate Time Series](https://mlsanity.com/paper/2011.01843/) (2020)
- [The autofeat Python Library for Automated Feature Engineering and Selection](https://mlsanity.com/paper/1901.07329/) (2019)
- [AMLB: an AutoML Benchmark](https://mlsanity.com/paper/2207.12560/) (2022)
- [OpenFE: Automated Feature Generation with Expert-level Performance](https://mlsanity.com/paper/2211.12507/) (2022)
- [Do Vision and Language Encoders Represent the World Similarly?](https://mlsanity.com/paper/2401.05224/) (2024)
- [LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers](https://mlsanity.com/paper/2503.14434/) (2025)
- [CoLES: Contrastive Learning for Event Sequences with Self-Supervision](https://mlsanity.com/paper/2002.08232/) (2020)
- [LightAutoML: AutoML Solution for a Large Financial Services Ecosystem](https://mlsanity.com/paper/2109.01528/) (2021)
- [Emergence and Evolution of Interpretable Concepts in Diffusion Models](https://mlsanity.com/paper/2504.15473/) (2025)
- [Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?](https://mlsanity.com/paper/2510.24709/) (2025)
- [UniTraj: Learning a Universal Trajectory Foundation Model from Billion-Scale Worldwide Traces](https://mlsanity.com/paper/2411.03859/) (2024)
- [Demystifying Embedding Spaces using Large Language Models](https://mlsanity.com/paper/2310.04475/) (2023)
- [Head Pursuit: Probing Attention Specialization in Multimodal Transformers](https://mlsanity.com/paper/2510.21518/) (2025)
- [Measuring and Guiding Monosemanticity](https://mlsanity.com/paper/2506.19382/) (2025)
- [Multimodal Banking Dataset: Understanding Client Needs through Event Sequences](https://mlsanity.com/paper/2409.17587/) (2024)
- [Rethinking the Privacy of Text Embeddings: A Reproducibility Study of "Text Embeddings Reveal (Almost) As Much As Text"](https://mlsanity.com/paper/2507.07700/) (2025)
- [Urania: Differentially Private Insights into AI Use](https://mlsanity.com/paper/2506.04681/) (2025)
- [LLM4ES: Learning User Embeddings from Event Sequences via Large Language Models](https://mlsanity.com/paper/2508.05688/) (2025)
- [Encode Me If You Can: Learning Universal User Representations via Event Sequence Autoencoding](https://mlsanity.com/paper/2508.07748/) (2025)
- [Deep Evolutional Instant Interest Network for CTR Prediction in Trigger-Induced Recommendation](https://mlsanity.com/paper/2401.07769/) (2024)
- [Tabular Feature Discovery With Reasoning Type Exploration](https://mlsanity.com/paper/2506.20357/) (2025)
- [MLOps: A Multiple Case Study in Industry 4.0](https://mlsanity.com/paper/2407.09107/) (2024)
- [LATTE: Learning Aligned Transactions and Textual Embeddings for Bank Clients](https://mlsanity.com/paper/2508.10021/) (2025)
- [Topological Metric for Unsupervised Embedding Quality Evaluation](https://mlsanity.com/paper/2512.15285/) (2025)
- [Compact Representations of Event Sequences](https://mlsanity.com/paper/1803.02576/) (2018)

## Built on by (most cited first, 1 of 1)

- [User-Centric Modeling of Transactional Sequences with Explainable State Space Models](https://mlsanity.com/paper/2607.20228/) (2026)

## Abstract (arXiv)

Industrial financial systems operate on temporal event sequences such as transactions, user actions, and system logs. While recent research emphasizes representation learning and large language models, production systems continue to rely heavily on handcrafted statistical features due to their interpretability, robustness under limited supervision, and strict latency constraints. This creates a persistent disconnect between learned embeddings and feature-based pipelines. We introduce Embedding-Aware Feature Discovery (EAFD), a unified framework that bridges this gap by coupling pretrained event-sequence embeddings with a self-reflective LLM-driven feature generation agent. EAFD iteratively discovers, evaluates, and refines features directly from raw event sequences using two complementary criteria: alignment, which explains information already encoded in embeddings, and complementarity, which identifies predictive signals missing from them. Across both open-source and industrial transaction benchmarks, EAFD consistently outperforms embedding-only and feature-based baselines, achieving relative gains of up to +5.8% over state-of-the-art pretrained embeddings, resulting in new state-of-the-art performance across event-sequence datasets.