Young‐Jin Park

Kashif Rasul, Young-Jin Park, Max Nihlén Ramström et al.

Time series models aim for accurate predictions of the future given the past, where the forecasts are used for important downstream tasks like business decision making. In practice, deep learning based time series models come in many forms, but at a high level learn some continuous representation of the past and use it to output point or probabilistic forecasts. In this paper, we introduce a novel autoregressive architecture, VQ-AR, which instead learns a \emph{discrete} set of representations that are used to predict the future. Extensive empirical comparison with other competitive deep learning models shows that surprisingly such a discrete set of representations gives state-of-the-art or equivalent results on a wide variety of time series datasets. We also highlight the shortcomings of this approach, explore its zero-shot generalization capabilities, and present an ablation study on the number of representations. The full source code of the method will be available at the time of publication with the hope that researchers can further investigate this important but overlooked inductive bias for the time series domain.

Young-Jin Park, Donghyun Kim, Frédéric Odermatt et al.

Time series forecasting is one of the most essential and ubiquitous tasks in many business problems, including demand forecasting and logistics optimization. Traditional time series forecasting methods, however, have resulted in small models with limited expressive power because they have difficulty in scaling their model size up while maintaining high accuracy. In this paper, we propose Forecasting orchestra (Forchestra), a simple but powerful framework capable of accurately predicting future demand for a diverse range of items. We empirically demonstrate that the model size is scalable to up to 0.8 billion parameters. The proposed method not only outperforms existing forecasting models with a significant margin, but it could generalize well to unseen data points when evaluated in a zero-shot fashion on downstream datasets. Last but not least, we present extensive qualitative and quantitative studies to analyze how the proposed model outperforms baseline models and differs from conventional approaches. The original paper was presented as a full paper at ICDM 2022 and is available at: https://ieeexplore.ieee.org/document/10027662.

Young-Jin Park, Kristjan Greenewald, Kaveh Alim et al. · mit

Process reward models (PRMs) play a central role in guiding inference-time scaling algorithms for large language models (LLMs). However, we observe that even state-of-the-art PRMs can be poorly calibrated. Specifically, they tend to overestimate the success probability that a partial reasoning step will lead to a correct final answer, particularly when smaller LLMs are used to complete the reasoning trajectory. To address this, we present a calibration approach -- performed via quantile regression -- that adjusts PRM outputs to better align with true success probabilities. Leveraging these calibrated success estimates and their associated confidence bounds, we introduce an \emph{instance-adaptive scaling} (IAS) framework that dynamically adjusts the compute budget based on the estimated likelihood that a partial reasoning trajectory will yield a correct final answer. Unlike conventional methods that allocate a fixed number of reasoning trajectories per query, this approach adapts to each instance and reasoning step when using our calibrated PRMs. Experiments on mathematical reasoning benchmarks show that (i) our PRM calibration method achieves small calibration error, outperforming the baseline methods, (ii) calibration is crucial for enabling effective IAS, and (iii) the proposed IAS strategy reduces inference costs while maintaining final answer accuracy, utilizing less compute on more confident problems as desired.

Young-Jin Park, Carson Sobolewski, Navid Azizan · mit

DEtection TRansformer (DETR) has emerged as a promising architecture for object detection, offering an end-to-end prediction pipeline. In practice, however, DETR generates hundreds of predictions that far outnumber the actual number of objects present in an image. This raises the question: can we trust and use all of these predictions? Addressing this concern, we present empirical evidence highlighting how different predictions within the same image play distinct roles, resulting in varying reliability levels across those predictions. More specifically, while multiple predictions are often made for a single object, our findings show that most often one such prediction is well-calibrated, and the others are poorly calibrated. Based on these insights, we demonstrate that identifying a reliable subset of DETR's predictions is crucial for accurately assessing the reliability of the model at both object and image levels. Building on this viewpoint, we first address the shortcomings of widely used performance and calibration metrics, such as average precision and various forms of expected calibration error. Specifically, they are inadequate for determining which subset of DETR's predictions should be trusted and utilized. In response, we present Object-level Calibration Error (OCE), which assesses the calibration quality more effectively and is suitable for both ranking different models and identifying the most reliable predictions within a specific model. As a final contribution, we introduce a post hoc uncertainty quantification (UQ) framework that predicts the accuracy of the model on a per-image basis. By contrasting the average confidence scores of positive (i.e., likely to be matched) and negative predictions determined by OCE, our framework assesses the reliability of the DETR model for each test image.

Ji Young Byun, Young-Jin Park, Navid Azizan et al. · mit

As a cornerstone of patient care, clinical decision-making significantly influences patient outcomes and can be enhanced by large language models (LLMs). Although LLMs have demonstrated remarkable performance, their application to visual question answering in medical imaging, particularly for reasoning-based diagnosis, remains largely unexplored. Furthermore, supervised fine-tuning for reasoning tasks is largely impractical due to limited data availability and high annotation costs. In this work, we introduce a zero-shot framework for reliable medical image diagnosis that enhances the reasoning capabilities of LLMs in clinical settings through test-time scaling. Given a medical image and a textual prompt, a vision-language model processes a medical image along with a corresponding textual prompt to generate multiple descriptions or interpretations of visual features. These interpretations are then fed to an LLM, where a test-time scaling strategy consolidates multiple candidate outputs into a reliable final diagnosis. We evaluate our approach across various medical imaging modalities -- including radiology, ophthalmology, and histopathology -- and demonstrate that the proposed test-time scaling strategy enhances diagnostic accuracy for both our and baseline methods. Additionally, we provide an empirical analysis showing that the proposed approach, which allows unbiased prompting in the first stage, improves the reliability of LLM-generated diagnoses and enhances classification accuracy.

Young-Jin Park, Hao Wang, Shervin Ardeshir et al.

Self-supervised learning models extract general-purpose representations from data. Quantifying the reliability of these representations is crucial, as many downstream models rely on them as input for their own tasks. To this end, we introduce a formal definition of representation reliability: the representation for a given test point is considered to be reliable if the downstream models built on top of that representation can consistently generate accurate predictions for that test point. However, accessing downstream data to quantify the representation reliability is often infeasible or restricted due to privacy concerns. We propose an ensemble-based method for estimating the representation reliability without knowing the downstream tasks a priori. Our method is based on the concept of neighborhood consistency across distinct pre-trained representation spaces. The key insight is to find shared neighboring points as anchors to align these representation spaces before comparing them. We demonstrate through comprehensive numerical experiments that our method effectively captures the representation reliability with a high degree of correlation, achieving robust and favorable performance compared with baseline methods.

Kyuyong Shin, Hanock Kwak, Kyung-Min Kim et al.

General-purpose representation learning through large-scale pre-training has shown promising results in the various machine learning fields. For an e-commerce domain, the objective of general-purpose, i.e., one for all, representations would be efficient applications for extensive downstream tasks such as user profiling, targeting, and recommendation tasks. In this paper, we systematically compare the generalizability of two learning strategies, i.e., transfer learning through the proposed model, ShopperBERT, vs. learning from scratch. ShopperBERT learns nine pretext tasks with 79.2M parameters from 0.8B user behaviors collected over two years to produce user embeddings. As a result, the MLPs that employ our embedding method outperform more complex models trained from scratch for five out of six tasks. Specifically, the pre-trained embeddings have superiority over the task-specific supervised features and the strong baselines, which learn the auxiliary dataset for the cold-start problem. We also show the computational efficiency and embedding visualization of the pre-trained features.

Seungjae Jung, Kyung-Min Kim, Hanock Kwak et al.

Probabilistic time-series models become popular in the forecasting field as they help to make optimal decisions under uncertainty. Despite the growing interest, a lack of thorough analysis hinders choosing what is worth applying for the desired task. In this paper, we analyze the performance of three prominent probabilistic time-series models for sales forecasting. To remove the role of random chance in architecture's performance, we make two experimental principles; 1) Large-scale dataset with various cross-validation sets. 2) A standardized training and hyperparameter selection. The experimental results show that a simple Multi-layer Perceptron and Linear Regression outperform the probabilistic models on RMSE without any feature engineering. Overall, the probabilistic models fail to achieve better performance on point estimation, such as RMSE and MAPE, than comparably simple baselines. We analyze and discuss the performances of probabilistic time-series models.

Youngjin Park, Deokjun Eom, Byoungki Seo et al.

Forecasting with multivariate time series, which aims to predict future values given previous and current several univariate time series data, has been studied for decades, with one example being ARIMA. Because it is difficult to measure the extent to which noise is mixed with informative signals within rapidly fluctuating financial time series data, designing a good predictive model is not a simple task. Recently, many researchers have become interested in recurrent neural networks and attention-based neural networks, applying them in financial forecasting. There have been many attempts to utilize these methods for the capturing of long-term temporal dependencies and to select more important features in multivariate time series data in order to make accurate predictions. In this paper, we propose a new prediction framework based on deep neural networks and a trend filtering, which converts noisy time series data into a piecewise linear fashion. We reveal that the predictive performance of deep temporal neural networks improves when the training data is temporally processed by a trend filtering. To verify the effect of our framework, three deep temporal neural networks, state of the art models for predictions in time series finance data, are used and compared with models that contain trend filtering as an input feature. Extensive experiments on real-world multivariate time series data show that the proposed method is effective and significantly better than existing baseline methods.

Jisu Jeong, Jeong-Min Yun, Hongi Keam et al.

Recently, the interest of graph representation learning has been rapidly increasing in recommender systems. However, most existing studies have focused on improving accuracy, but in real-world systems, the recommendation diversity should be considered as well to improve user experiences. In this paper, we propose the diversity-emphasized node embedding div2vec, which is a random walk-based unsupervised learning method like DeepWalk and node2vec. When generating random walks, DeepWalk and node2vec sample nodes of higher degree more and nodes of lower degree less. On the other hand, div2vec samples nodes with the probability inversely proportional to its degree so that every node can evenly belong to the collection of random walks. This strategy improves the diversity of recommendation models. Offline experiments on the MovieLens dataset showed that our new method improves the recommendation performance in terms of both accuracy and diversity. Moreover, we evaluated the proposed model on two real-world services, WATCHA and LINE Wallet Coupon, and observed the div2vec improves the recommendation quality by diversifying the system.

Young-Jin Park, Kyuyong Shin, Kyung-Min Kim

Graph representation learning is gaining popularity in a wide range of applications, such as social networks analysis, computational biology, and recommender systems. However, different with positive results from many academic studies, applying graph neural networks (GNNs) in a real-world application is still challenging due to non-stationary environments. The underlying distribution of streaming data changes unexpectedly, resulting in different graph structures (a.k.a., concept drift). Therefore, it is essential to devise a robust graph learning technique so that the model does not overfit to the training graphs. In this work, we present Hop Sampling, a straightforward regularization method that can effectively prevent GNNs from overfishing. The hop sampling randomly selects the number of propagation steps rather than fixing it, and by doing so, it encourages the model to learn meaningful node representation for all intermediate propagation layers and to experience a variety of plausible graphs that are not in the training set. Particularly, we describe the use case of our method in recommender systems, a representative example of the real-world non-stationary case. We evaluated hop sampling on a large-scale real-world LINE dataset and conducted an online A/B/n test in LINE Coupon recommender systems of LINE Wallet Tab. Experimental results demonstrate that the proposed scheme improves the prediction accuracy of GNNs. We observed hop sampling provides 7.97% and 16.93% improvements for NDCG and MAP compared to non-regularized GNN models in our online service. Furthermore, models using hop sampling alleviate the oversmoothing issue in GNNs enabling a deeper model as well as more diversified representation.

Young-Jin Park, Han-Lim Choi

The goal of system identification is to learn about underlying physics dynamics behind the time-series data. To model the probabilistic and nonparametric dynamics model, Gaussian process (GP) have been widely used; GP can estimate the uncertainty of prediction and avoid over-fitting. Traditional GPSSMs, however, are based on Gaussian transition model, thus often have difficulty in describing a more complex transition model, e.g. aircraft motions. To resolve the challenge, this paper proposes a framework using multiple GP transition models which is capable of describing multi-modal dynamics. Furthermore, we extend the model to the information-theoretic framework, the so-called InfoSSM, by introducing a mutual information regularizer helping the model to learn interpretable and distinguishable multiple dynamics models. Two illustrative numerical experiments in simple Dubins vehicle and high-fidelity flight simulator are presented to demonstrate the performance and interpretability of the proposed model. Finally, this paper introduces a framework using InfoSSM with Bayesian filtering for air traffic control tracking.