arXiv subjects

Alexey Vasilev

Publications and source records attributed to Alexey Vasilev.

At least 19 recordsLinked to original sources

arXiv2026

A Foundation Model for Multimodal Event Sequences in Financial Applications

Predictive modeling is a core component of modern financial services, where a wide range of tasks are traditionally addressed using separate models trained on manually engineered tabular features. This task-specific approach limits reuse and makes it difficult to fully exploit heterogeneous data sources such as transaction histories and digital interaction signals. In this paper, we present an approach based on pretraining a foundation transformer model on multimodal sequences of user events. Events from multiple data sources are unified into a single chronological sequence, enabling early fusion of heterogeneous modalities and learning of general-purpose representations via a next-event prediction objective. These representations are combined with existing engineered user features, on top of which lightweight neural models are trained for multiple downstream tasks. The proposed system outperforms traditional task-specific models while reducing development overhead. The approach was deployed in production at one of the biggest banks in Eastern Europe, resulting in measurable improvements in business metrics.

cs.LG↗

arXiv2026

Faster and Memory-Efficient Training of Sequential Recommendation Models for Large Catalogs

Sequential recommendations (SR) with transformer-based architectures are widely adopted in real-world applications, where SR models require frequent retraining to adapt to ever-changing user preferences. However, training transformer-based SR models often encounters a high computational cost associated with scoring extensive item catalogs, often exceeding thousands of items. This occurs mainly due to the use of cross-entropy loss, where peak memory scales proportionally to catalog size, batch size, and sequence length. Recognizing this, practitioners in the field of recommendation systems typically address memory consumption by integrating the cross-entropy (CE) loss with negative sampling, thereby reducing the explicit memory demands of the final layer. However, a small number of negative samples would degrade model performance, and as we demonstrate in our work, increasing the number of negative samples and the batch size further improves the model's performance, but rapidly starts to exceed industrial GPUs' size (~40Gb). In this work, we introduce the CCE- method, which offers a GPU-efficient implementation of the CE loss with negative sampling. Our method accelerates training by up to two times while reducing memory consumption by more than 10 times. Leveraging the memory savings afforded by using CCE- for model training, it becomes feasible to enhance its accuracy on datasets with a large item catalog compared to those trained with original PyTorch-implemented loss functions. Finally, we perform an analysis of key memory-related hyperparameters and highlight the necessity of a delicate balance among these factors. We demonstrate that scaling both the number of negative samples and batch size leads to better results rather than maximizing only one of them. To facilitate further adoption of CCE-, we release a Triton kernel that efficiently implements the proposed method.

cs.IR↗

arXiv2026

Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation

Sequential recommender systems have achieved significant success in modeling temporal user behavior but remain limited in capturing rich user semantics beyond interaction patterns. Large Language Models (LLMs) present opportunities to enhance user understanding with their reasoning capabilities, yet existing integration approaches create prohibitive inference costs in real time. To address these limitations, we present a novel knowledge distillation method that utilizes textual user profile generated by pre-trained LLMs into sequential recommenders without requiring LLM inference at serving time. The resulting approach maintains the inference efficiency of traditional sequential models while requiring neither architectural modifications nor LLM fine-tuning.

cs.IR↗

arXiv2026

Room-temperature, continuous wave lasing in planar microcavities with quantum dots

High-quality planar cavities with low-absorption mirrors based on $Al_{0.2}Ga_{0.8}As/Al_{0.9}Ga_{0.1}As$ layers demonstrate continuous wave lasing at a wavelength of 956 nm. At 300 K, the threshold power density and quality-factor at the threshold are (4.2$\pm$0.3) $kW/cm^2$ and (6800$\pm$220). Increasing the pump level above two thresholds lead to an enlargement in the quality-factor to at least 19000. Efficient lateral heat dissipation in the planar semiconductor microcavity is confirmed by a low mode-energy shift of approximately 400 $\mu$eV at two lasing thresholds.

physics.optics↗

arXiv2026

SplitLight: An Exploratory Toolkit for Recommender Systems Datasets and Splits

Offline evaluation of recommender systems is often affected by hidden, under-documented choices in data preparation. Seemingly minor decisions in filtering, handling repeats, cold-start treatment, and splitting strategy design can substantially reorder model rankings and undermine reproducibility and cross-paper comparability. In this paper, we introduce SplitLight, an open-source exploratory toolkit that enables researchers and practitioners designing preprocessing and splitting pipelines or reviewing external artifacts to make these decisions measurable, comparable, and reportable. Given an interaction log and derived split subsets, SplitLight analyzes core and temporal dataset statistics, characterizes repeat consumption patterns and timestamp anomalies, and diagnoses split validity, including temporal leakage, cold-user/item exposure, and distribution shifts. SplitLight further allows side-by-side comparison of alternative splitting strategies through comprehensive aggregated summaries and interactive visualizations. Delivered as both a Python toolkit and an interactive no-code interface, SplitLight produces audit summaries that justify evaluation protocols and support transparent, reliable, and comparable experimentation in recommender systems research and industry.

cs.IR↗

arXiv2026

Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their internals can help understand, influence, and control their behavior, which is very important in a variety of real-world applications. Recently, sparse autoencoders (SAE) have been shown to be a promising unsupervised approach to extract interpretable features from neural networks. In this work, we extend SAE to sequential recommender systems and propose a framework for interpreting and controlling model representations. We show that this approach can be successfully applied to the transformer trained on a sequential recommendation task: directions learned in such an unsupervised regime turn out to be more interpretable and monosemantic than the original hidden state dimensions. Further, we demonstrate a straightforward way to effectively and flexibly control the model's behavior, giving developers and users of recommendation systems the ability to adjust their recommendations to various custom scenarios and contexts.

cs.IR↗

arXiv2025

Benefiting from Negative yet Informative Feedback by Contrasting Opposing Sequential Patterns

We consider the task of learning from both positive and negative feedback in a sequential recommendation scenario, as both types of feedback are often present in user interactions. Meanwhile, conventional sequential learning models usually focus on considering and predicting positive interactions, ignoring that reducing items with negative feedback in recommendations improves user satisfaction with the service. Moreover, the negative feedback can potentially provide a useful signal for more accurate identification of true user interests. In this work, we propose to train two transformer encoders on separate positive and negative interaction sequences. We incorporate both types of feedback into the training objective of the sequential recommender using a composite loss function that includes positive and negative cross-entropy as well as a cleverly crafted contrastive term, that helps better modeling opposing patterns. We demonstrate the effectiveness of this approach in terms of increasing true-positive metrics compared to state-of-the-art sequential recommendation methods while reducing the number of wrongly promoted negative items.

cs.IR↗

arXiv2025

Encode Me If You Can: Learning Universal User Representations via Event Sequence Autoencoding

Building universal user representations that capture the essential aspects of user behavior is a crucial task for modern machine learning systems. In real-world applications, a user's historical interactions often serve as the foundation for solving a wide range of predictive tasks, such as churn prediction, recommendations, or lifetime value estimation. Using a task-independent user representation that is effective across all such tasks can reduce the need for task-specific feature engineering and model retraining, leading to more scalable and efficient machine learning pipelines. The goal of the RecSys Challenge 2025 by Synerise was to develop such Universal Behavioral Profiles from logs of past user behavior, which included various types of events such as product purchases, page views, and search queries. We propose a method that transforms the entire user interaction history into a single chronological sequence and trains a GRU-based autoencoder to reconstruct this sequence from a fixed-size vector. If the model can accurately reconstruct the sequence, the latent vector is expected to capture the key behavioral patterns. In addition to this core model, we explored several alternative methods for generating user embeddings and combined them by concatenating their output vectors into a unified representation. This ensemble strategy further improved generalization across diverse downstream tasks and helped our team, ai_lab_recsys, achieve second place in the RecSys Challenge 2025.

cs.IR↗

arXiv2025

Let It Go? Not Quite: Addressing Item Cold Start in Sequential Recommendations with Content-Based Initialization

Many sequential recommender systems suffer from the cold start problem, where items with few or no interactions cannot be effectively used by the model due to the absence of a trained embedding. Content-based approaches, which leverage item metadata, are commonly used in such scenarios. One possible way is to use embeddings derived from content features such as textual descriptions as initialization for the model embeddings. However, directly using frozen content embeddings often results in suboptimal performance, as they may not fully adapt to the recommendation task. On the other hand, fine-tuning these embeddings can degrade performance for cold-start items, as item representations may drift far from their original structure after training. We propose a novel approach to address this limitation. Instead of entirely freezing the content embeddings or fine-tuning them extensively, we introduce a small trainable delta to frozen embeddings that enables the model to adapt item representations without letting them go too far from their original semantic structure. This approach demonstrates consistent improvements across multiple datasets and modalities, including e-commerce datasets with textual descriptions and a music dataset with audio-based representation.

cs.IR↗

arXiv2025

Time to Split: Exploring Data Splitting Strategies for Offline Evaluation of Sequential Recommenders

Modern sequential recommender systems, ranging from lightweight transformer-based variants to large language models, have become increasingly prominent in academia and industry due to their strong performance in the next-item prediction task. Yet common evaluation protocols for sequential recommendations remain insufficiently developed: they often fail to reflect the corresponding recommendation task accurately, or are not aligned with real-world scenarios. Although the widely used leave-one-out split matches next-item prediction, it permits the overlap between training and test periods, which leads to temporal leakage and unrealistically long test horizon, limiting real-world relevance. Global temporal splitting addresses these issues by evaluating on distinct future periods. However, its applications to sequential recommendations remain loosely defined, particularly in terms of selecting target interactions and constructing a validation subset that provides necessary consistency between validation and test metrics. In this paper, we demonstrate that evaluation outcomes can vary significantly across splitting strategies, influencing model rankings and practical deployment decisions. To improve reproducibility in both academic and industrial settings, we systematically compare different splitting strategies for sequential recommendations across multiple datasets and established baselines. Our findings show that prevalent splits, such as leave-one-out, may be insufficiently aligned with more realistic evaluation strategies. Code: https://github.com/monkey0head/time-to-split

cs.IR↗

arXiv2024

RePlay: a Recommendation Framework for Experimentation and Production Use

Using a single tool to build and compare recommender systems significantly reduces the time to market for new models. In addition, the comparison results when using such tools look more consistent. This is why many different tools and libraries for researchers in the field of recommendations have recently appeared. Unfortunately, most of these frameworks are aimed primarily at researchers and require modification for use in production due to the inability to work on large datasets or an inappropriate architecture. In this demo, we present our open-source toolkit RePlay - a framework containing an end-to-end pipeline for building recommender systems, which is ready for production use. RePlay also allows you to use a suitable stack for the pipeline on each stage: Pandas, Polars, or Spark. This allows the library to scale computations and deploy to a cluster. Thus, RePlay allows data scientists to easily move from research mode to production mode using the same interfaces.

cs.IR↗

arXiv2024

Stalactite: Toolbox for Fast Prototyping of Vertical Federated Learning Systems

Machine learning (ML) models trained on datasets owned by different organizations and physically located in remote databases offer benefits in many real-world use cases. State regulations or business requirements often prevent data transfer to a central location, making it difficult to utilize standard machine learning algorithms. Federated Learning (FL) is a technique that enables models to learn from distributed datasets without revealing the original data. Vertical Federated learning (VFL) is a type of FL where data samples are divided by features across several data owners. For instance, in a recommendation task, a user can interact with various sets of items, and the logs of these interactions are stored by different organizations. In this demo paper, we present \emph{Stalactite} - an open-source framework for VFL that provides the necessary functionality for building prototypes of VFL systems. It has several advantages over the existing frameworks. In particular, it allows researchers to focus on the algorithmic side rather than engineering and to easily deploy learning in a distributed environment. It implements several VFL algorithms and has a built-in homomorphic encryption layer. We demonstrate its use on a real-world recommendation datasets.

cs.LG↗

arXiv2024

Neural Click Models for Recommender Systems

We develop and evaluate neural architectures to model the user behavior in recommender systems (RS) inspired by click models for Web search but going beyond standard click models. Proposed architectures include recurrent networks, Transformer-based models that alleviate the quadratic complexity of self-attention, adversarial and hierarchical architectures. Our models outperform baselines on the ContentWise and RL4RS datasets and can be used in RS simulators to model user response for RS evaluation and pretraining.

cs.IR↗

arXiv2024

Autoregressive Generation Strategies for Top-K Sequential Recommendations

The goal of modern sequential recommender systems is often formulated in terms of next-item prediction. In this paper, we explore the applicability of generative transformer-based models for the Top-K sequential recommendation task, where the goal is to predict items a user is likely to interact with in the "near future". We explore commonly used autoregressive generation strategies, including greedy decoding, beam search, and temperature sampling, to evaluate their performance for the Top-K sequential recommendation task. In addition, we propose novel Reciprocal Rank Aggregation (RRA) and Relevance Aggregation (RA) generation strategies based on multi-sequence generation with temperature sampling and subsequent aggregation. Experiments on diverse datasets give valuable insights regarding commonly used strategies' applicability and show that suggested approaches improve performance on longer time horizons compared to widely-used Top-K prediction approach and single-sequence autoregressive generation strategies.

cs.IR↗

arXiv2024

Cross-Domain Latent Factors Sharing via Implicit Matrix Factorization

Data sparsity has been one of the long-standing problems for recommender systems. One of the solutions to mitigate this issue is to exploit knowledge available in other source domains. However, many cross-domain recommender systems introduce a complex architecture that makes them less scalable in practice. On the other hand, matrix factorization methods are still considered to be strong baselines for single-domain recommendations. In this paper, we introduce the CDIMF, a model that extends the standard implicit matrix factorization with ALS to cross-domain scenarios. We apply the Alternating Direction Method of Multipliers to learn shared latent factors for overlapped users while factorizing the interaction matrix. In a dual-domain setting, experiments on industrial datasets demonstrate a competing performance of CDIMF for both cold-start and warm-start. The proposed model can outperform most other recent cross-domain and single-domain models. We also provide the code to reproduce experiments on GitHub.

cs.IR↗

arXiv2024

From Variability to Stability: Advancing RecSys Benchmarking Practices

In the rapidly evolving domain of Recommender Systems (RecSys), new algorithms frequently claim state-of-the-art performance based on evaluations over a limited set of arbitrarily selected datasets. However, this approach may fail to holistically reflect their effectiveness due to the significant impact of dataset characteristics on algorithm performance. Addressing this deficiency, this paper introduces a novel benchmarking methodology to facilitate a fair and robust comparison of RecSys algorithms, thereby advancing evaluation practices. By utilizing a diverse set of $30$ open datasets, including two introduced in this work, and evaluating $11$ collaborative filtering algorithms across $9$ metrics, we critically examine the influence of dataset characteristics on algorithm performance. We further investigate the feasibility of aggregating outcomes from multiple datasets into a unified ranking. Through rigorous experimental analysis, we validate the reliability of our methodology under the variability of datasets, offering a benchmarking strategy that balances quality and computational demands. This methodology enables a fair yet effective means of evaluating RecSys algorithms, providing valuable guidance for future research endeavors.

cs.IR↗

arXiv2024

Does It Look Sequential? An Analysis of Datasets for Evaluation of Sequential Recommendations

Sequential recommender systems are an important and demanded area of research. Such systems aim to use the order of interactions in a user's history to predict future interactions. The premise is that the order of interactions and sequential patterns play an essential role. Therefore, it is crucial to use datasets that exhibit a sequential structure to evaluate sequential recommenders properly. We apply several methods based on the random shuffling of the user's sequence of interactions to assess the strength of sequential structure across 15 datasets, frequently used for sequential recommender systems evaluation in recent research papers presented at top-tier conferences. As shuffling explicitly breaks sequential dependencies inherent in datasets, we estimate the strength of sequential patterns by comparing metrics for shuffled and original versions of the dataset. Our findings show that several popular datasets have a rather weak sequential structure.

cs.IR↗

arXiv2024

Low-Threshold Surface-Emitting Whispering-Gallery Mode Microlasers

We report on microlasers based on high-quality micropillars with lasing on whispering-gallery modes. Usage of low-absorbing Al$\scriptsize 0.2$Ga$\scriptsize 0.8$As\Al$\scriptsize 0.9$Ga$\scriptsize 0.1$As distributed Bragg reflectors as well as the smooth pillar sidewalls allows us to realize whispering-gallery modes lasing by excitation and collection of emission in the pillar axis direction. As a result, simultaneous whispering gallery modes lasing (comb-like structure) in the wavelength range of 930-970 nm is observed for 3-7 $μ$m pillar diameters. Increase the temperature up to 130 K results single-mode lasing for 5 $μ$m pillars with about 8000 cold cavity quality-factor and 240 $μ$W estimated threshold excitation power.

cond-mat.mes-hall↗