6 papers
Temporal graph models fail to capture global temporal dynamics
Michał Daniluk, Jacek Dąbrowski
A recently released Temporal Graph Benchmark is analyzed in the context of Dynamic Link Property Prediction. We outline our observations and propose a trivial optimization-free bas…
Synerise at RecSys 2021: Twitter user engagement prediction with a fast neural model
Michał Daniluk, Jacek Dąbrowski, Barbara Rychalska +1
In this paper we present our 2nd place solution to ACM RecSys 2021 Challenge organized by Twitter. The challenge aims to predict user engagement for a set of tweets, offering an ex…
Modeling Multi-Destination Trips with Sketch-Based Model
Michał Daniluk, Barbara Rychalska, Konrad Gołuchowski +1
The recently proposed EMDE (Efficient Manifold Density Estimator) model achieves state of-the-art results in session-based recommendation. In this work we explore its application t…
Cleora: A Simple, Strong and Scalable Graph Embedding Scheme
Barbara Rychalska, Piotr Bąbel, Konrad Gołuchowski +2
The area of graph embeddings is currently dominated by contrastive learning methods, which demand formulation of an explicit objective function and sampling of positive and negativ…
I know why you like this movie: Interpretable Efficient Multimodal Recommender
Barbara Rychalska, Dominika Basaj, Jacek Dąbrowski +1
Recently, the Efficient Manifold Density Estimator (EMDE) model has been introduced. The model exploits Local Sensitive Hashing and Count-Min Sketch algorithms, combining them with…
An efficient manifold density estimator for all recommendation systems
Jacek Dąbrowski, Barbara Rychalska, Michał Daniluk +5
Many unsupervised representation learning methods belong to the class of similarity learning models. While various modality-specific approaches exist for different types of data, a…