6 papers
When Losses Align: Gradient-Based Composite Loss Weighting for Efficient Pretraining
Ivan Karpukhin, Andrey Savchenko
Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple loss terms act as hyperparameters…
HT-Transformer: Event Sequences Classification by Accumulating Prefix Information with History Tokens
Ivan Karpukhin, Andrey Savchenko
Deep learning has achieved remarkable success in modeling sequential data, including event sequences, temporal point processes, and irregular time series. Recently, transformers ha…
Multimodal Banking Dataset: Understanding Client Needs through Event Sequences
Dzhambulat Mollaev, Alexander Kostin, Maria Postnova +4
Financial organizations collect a huge amount of temporal (sequential) data about clients, which is typically collected from multiple sources (modalities). Despite the urgent pract…
Detecting the Future: All-at-Once Event Sequence Forecasting with Horizon Matching
Ivan Karpukhin, Andrey Savchenko
Long-horizon events forecasting is a crucial task across various domains, including retail, finance, healthcare, and social networks. Traditional models for event sequences often e…
ESQA: Event Sequences Question Answering
Irina Abdullaeva, Andrei Filatov, Mikhail Orlov +6
Event sequences (ESs) arise in many practical domains including finance, retail, social networks, and healthcare. In the context of machine learning, event sequences can be seen as…
HoTPP Benchmark: Are We Good at the Long Horizon Events Forecasting?
Ivan Karpukhin, Foma Shipilov, Andrey Savchenko
Forecasting multiple future events within a given time horizon is essential for applications in finance, retail, social networks, and healthcare. Marked Temporal Point Processes (M…