Nam H. Nguyen

Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong et al.

We propose an efficient design of Transformer-based models for multivariate time series forecasting and self-supervised representation learning. It is based on two key components: (i) segmentation of time series into subseries-level patches which are served as input tokens to Transformer; (ii) channel-independence where each channel contains a single univariate time series that shares the same embedding and Transformer weights across all the series. Patching design naturally has three-fold benefit: local semantic information is retained in the embedding; computation and memory usage of the attention maps are quadratically reduced given the same look-back window; and the model can attend longer history. Our channel-independent patch time series Transformer (PatchTST) can improve the long-term forecasting accuracy significantly when compared with that of SOTA Transformer-based models. We also apply our model to self-supervised pre-training tasks and attain excellent fine-tuning performance, which outperforms supervised training on large datasets. Transferring of masked pre-trained representation on one dataset to others also produces SOTA forecasting accuracy. Code is available at: https://github.com/yuqinie98/PatchTST.

Filippos Bellos, NaveenJohn Premkumar, Yannis Avrithis et al.

LLM-for-time series (TS) methods typically treat time shallowly, injecting positional or prompt-based cues once at the input of a largely frozen decoder, which limits temporal reasoning as this information degrades through the layers. We introduce Temporal-Prior Conditioning (TPC), which elevates time to a first-class modality that conditions the model at multiple depths. TPC attaches a small set of learnable time series tokens to the patch stream; at selected layers these tokens cross-attend to temporal embeddings derived from compact, human-readable temporal descriptors encoded by the same frozen LLM, then feed temporal context back via self-attention. This disentangles time series signal and temporal information while maintaining a low parameter budget. We show that by training only the cross-attention modules and explicitly disentangling time series signal and temporal information, TPC consistently outperforms both full fine-tuning and shallow conditioning strategies, achieving state-of-the-art performance in long-term forecasting across diverse datasets. Code available at: https://github.com/fil-mp/Deep_tpc

Zepu Wang, Yuqi Nie, Peng Sun et al.

The criticality of prompt and precise traffic forecasting in optimizing traffic flow management in Intelligent Transportation Systems (ITS) has drawn substantial scholarly focus. Spatio-Temporal Graph Neural Networks (STGNNs) have been lauded for their adaptability to road graph structures. Yet, current research on STGNNs architectures often prioritizes complex designs, leading to elevated computational burdens with only minor enhancements in accuracy. To address this issue, we propose ST-MLP, a concise spatio-temporal model solely based on cascaded Multi-Layer Perceptron (MLP) modules and linear layers. Specifically, we incorporate temporal information, spatial information and predefined graph structure with a successful implementation of the channel-independence strategy - an effective technique in time series forecasting. Empirical results demonstrate that ST-MLP outperforms state-of-the-art STGNNs and other models in terms of accuracy and computational efficiency. Our finding encourages further exploration of more concise and effective neural network architectures in the field of traffic forecasting.

Santosh Palaskar, Vijay Ekambaram, Arindam Jati et al.

The efficiency of business processes relies on business key performance indicators (Biz-KPIs), that can be negatively impacted by IT failures. Business and IT Observability (BizITObs) data fuses both Biz-KPIs and IT event channels together as multivariate time series data. Forecasting Biz-KPIs in advance can enhance efficiency and revenue through proactive corrective measures. However, BizITObs data generally exhibit both useful and noisy inter-channel interactions between Biz-KPIs and IT events that need to be effectively decoupled. This leads to suboptimal forecasting performance when existing multivariate forecasting models are employed. To address this, we introduce AutoMixer, a time-series Foundation Model (FM) approach, grounded on the novel technique of channel-compressed pretrain and finetune workflows. AutoMixer leverages an AutoEncoder for channel-compressed pretraining and integrates it with the advanced TSMixer model for multivariate time series forecasting. This fusion greatly enhances the potency of TSMixer for accurate forecasts and also generalizes well across several downstream tasks. Through detailed experiments and dashboard analytics, we show AutoMixer's capability to consistently improve the Biz-KPI's forecasting accuracy (by 11-15\%) which directly translates to actionable business insights.

Vijay Ekambaram, Arindam Jati, Pankaj Dayama et al.

Large pre-trained models excel in zero/few-shot learning for language and vision tasks but face challenges in multivariate time series (TS) forecasting due to diverse data characteristics. Consequently, recent research efforts have focused on developing pre-trained TS forecasting models. These models, whether built from scratch or adapted from large language models (LLMs), excel in zero/few-shot forecasting tasks. However, they are limited by slow performance, high computational demands, and neglect of cross-channel and exogenous correlations. To address this, we introduce Tiny Time Mixers (TTM), a compact model (starting from 1M parameters) with effective transfer learning capabilities, trained exclusively on public TS datasets. TTM, based on the light-weight TSMixer architecture, incorporates innovations like adaptive patching, diverse resolution sampling, and resolution prefix tuning to handle pre-training on varied dataset resolutions with minimal model capacity. Additionally, it employs multi-level modeling to capture channel correlations and infuse exogenous signals during fine-tuning. TTM outperforms existing popular benchmarks in zero/few-shot forecasting by (4-40%), while reducing computational requirements significantly. Moreover, TTMs are lightweight and can be executed even on CPU-only machines, enhancing usability and fostering wider adoption in resource-constrained environments. The model weights for reproducibility and research use are available at https://huggingface.co/ibm/ttm-research-r2/, while enterprise-use weights under the Apache license can be accessed as follows: the initial TTM-Q variant at https://huggingface.co/ibm-granite/granite-timeseries-ttm-r1, and the latest variants (TTM-B, TTM-E, TTM-A) weights are available at https://huggingface.co/ibm-granite/granite-timeseries-ttm-r2.

Sravan Kumar Ankireddy, Nikita Seleznev, Nam H. Nguyen et al.

Transformer-based time series foundation models face a fundamental trade-off in choice of tokenization: point-wise embeddings preserve temporal fidelity but scale poorly with sequence length, whereas fixed-length patching improves efficiency by imposing uniform boundaries that may disrupt natural transitions and blur informative local dynamics. In order to address these limitations, we introduce TimeSqueeze, a dynamic patching mechanism that adaptively selects patch boundaries within each sequence based on local signal complexity. TimeSqueeze first applies a lightweight state-space encoder to extract full-resolution point-wise features, then performs content-aware segmentation by allocating short patches to information-dense regions and long patches to smooth or redundant segments. This variable-resolution compression preserves critical temporal structure while substantially reducing the token sequence presented to the Transformer backbone. Specifically for large-scale pretraining, TimeSqueeze attains up to 20x faster convergence and 8x higher data efficiency compared to equivalent point-token baselines. Experiments across long-horizon forecasting benchmarks show that TimeSqueeze consistently outperforms comparable architectures that use either point-wise tokenization or fixed-size patching.

Zefang Liu, Nam H. Nguyen, Yinzhu Quan et al.

Representing continuous time is a critical and under-explored challenge in modeling temporal event sequences with large language models (LLMs). Various strategies like byte-level representations or calendar tokens have been proposed. However, the optimal approach remains unclear, especially given the diverse statistical distributions of real-world event data, which range from smooth log-normal to discrete, spiky patterns. This paper presents the first empirical study of temporal tokenization for event sequences, comparing distinct encoding strategies: naive numeric strings, high-precision byte-level representations, human-semantic calendar tokens, classic uniform binning, and adaptive residual scalar quantization. We evaluate these strategies by fine-tuning LLMs on real-world datasets that exemplify these diverse distributions. Our analysis reveals that no single strategy is universally superior; instead, prediction performance depends heavily on aligning the tokenizer with the data's statistical properties, with log-based strategies excelling on skewed distributions and human-centric formats proving robust for mixed modalities.

Yulun Wu, Sravan Kumar Ankireddy, Samuel Sharpe et al.

Efficiently aggregating spatial or temporal horizons to acquire compact representations has become a unifying principle in modern deep learning models, yet learning data-adaptive representations for long-horizon sequence data, especially continuous sequences like time series, remains an open challenge. While fixed-size patching has improved scalability and performance, discovering variable-sized, data-driven patches end-to-end often forces models to rely on soft discretization, specific backbones, or heuristic rules. In this work, we propose Reinforcement Patching (ReinPatch), the first framework to jointly optimize a sequence patching policy and its downstream sequence backbone model using reinforcement learning. By formulating patch boundary placement as a discrete decision process optimized via Group Relative Policy Gradient (GRPG), ReinPatch bypasses the need for continuous relaxations and performs dynamic patching policy optimization in a natural manner. Moreover, our method allows strict enforcement of a desired compression rate, freeing the downstream backbone to scale efficiently, and naturally supports multi-level hierarchical modeling. We evaluate ReinPatch on time-series forecasting datasets, where it demonstrates compelling performance compared to state-of-the-art data-driven patching strategies. Furthermore, our detached design allows the patching module to be extracted as a standalone foundation patcher, providing the community with visual and empirical insights into the segmentation behaviors preferred by a purely performance-driven neural patching strategy.

Su V. Huynh, Nam H. Nguyen, Ngoc T. Nguyen et al.

Vehicle Re-Identification (Re-ID) aims to identify the same vehicle across different cameras, hence plays an important role in modern traffic management systems. The technical challenges require the algorithms must be robust in different views, resolution, occlusion and illumination conditions. In this paper, we first analyze the main factors hindering the Vehicle Re-ID performance. We then present our solutions, specifically targeting the dataset Track 2 of the 5th AI City Challenge, including (1) reducing the domain gap between real and synthetic data, (2) network modification by stacking multi heads with attention mechanism, (3) adaptive loss weight adjustment. Our method achieves 61.34% mAP on the private CityFlow testset without using external dataset or pseudo labeling, and outperforms all previous works at 87.1% mAP on the Veri benchmark. The code is available at https://github.com/cybercore-co-ltd/track2_aicity_2021.

Nassima M. Bouzid, Dehao Yuan, Nam H. Nguyen et al.

LLM-based simulators offer a promising path for generating complex synthetic data where traditional differentially private (DP) methods struggle with high-dimensional user profiles. But can LLMs faithfully reproduce statistical distributions from DP-protected inputs? We evaluate this using PersonaLedger, an agentic financial simulator, seeded with DP synthetic personas derived from real user statistics. We find that PersonaLedger achieves promising fraud detection utility (AUC 0.70 at epsilon=1) but exhibits significant distribution drift due to systematic LLM biases--learned priors overriding input statistics for temporal and demographic features. These failure modes must be addressed before LLM-based methods can handle the richer user representations where they might otherwise excel.

Thomas D. P. Edwards, James Alvey, Justin Alsing et al.

Scaling laws for large language models (LLMs) have provided useful guidance in training ever larger models for predictable performance gains. Time series forecasting shares a similar sequential structure to language, and is amenable to large-scale transformer architectures. Here we show that foundational decoder-only time series transformer models exhibit analogous scaling-behavior to LLMs, with architectural details (aspect ratio and number of heads) having a minimal effect over broad ranges. We assemble a large corpus of heterogenous time series data on which to train, and establish for the first time power-law scaling with parameter count, dataset size, and training compute, spanning five orders of magnitude.

Filippos Bellos, Nam H. Nguyen, Jason J. Corso

Although LLMs have demonstrated remarkable capabilities in processing and generating textual data, their pre-trained vocabularies are ill-suited for capturing the nuanced temporal dynamics and patterns inherent in time series. The discrete, symbolic nature of natural language tokens, which these vocabularies are designed to represent, does not align well with the continuous, numerical nature of time series data. To address this fundamental limitation, we propose VITRO. Our method adapts textual inversion optimization from the vision-language domain in order to learn a new time series per-dataset vocabulary that bridges the gap between the discrete, semantic nature of natural language and the continuous, numerical nature of time series data. We show that learnable time series-specific pseudo-word embeddings represent time series data better than existing general language model vocabularies, with VITRO-enhanced methods achieving state-of-the-art performance in long-term forecasting across most datasets.

Rizal Fathony, Igor Melnyk, Owen Reinert et al.

User event modeling plays a central role in many machine learning applications, with use cases spanning e-commerce, social media, finance, cybersecurity, and other domains. User events can be broadly categorized into personal events, which involve individual actions, and relational events, which involve interactions between two users. These two types of events are typically modeled separately, using sequence-based methods for personal events and graph-based methods for relational events. Despite the need to capture both event types in real-world systems, prior work has rarely considered them together. This is often due to the convenient simplification that user behavior can be adequately represented by a single formalization, either as a sequence or a graph. To address this gap, there is a need for public datasets and prediction tasks that explicitly incorporate both personal and relational events. In this work, we introduce a collection of such datasets, propose a unified formalization, and empirically show that models benefit from incorporating both event types. Our results also indicate that current methods leave a notable room for improvements. We release these resources to support further research in unified user event modeling and encourage progress in this direction.

Yuen Chen, Yulun Wu, Samuel Sharpe et al.

Many real-world datasets are both sequential and relational: each node carries an event sequence while edges encode interactions. Existing methods in sequence modeling and graph modeling often neglect one modality or the other. We argue that sequences and graphs are not separate problems but complementary facets of the same dataset, and should be learned jointly. We introduce BRIDGE, a unified end-to-end architecture that couples a sequence encoder with a GNN under a single objective, allowing gradients to flow across both modules and learning task-aligned representations. To enable fine-grained token-level message passing among neighbors, we add TOKENXATTN, a token-level cross-attention layer that passes messages between events in neighboring sequences. Across two settings, friendship prediction (Brightkite) and fraud detection (Amazon), BRIDGE consistently outperforms static GNNs, temporal graph methods, and sequence-only baselines on ranking and classification metrics.

Sima E. Borujeni, Nam H. Nguyen, Saideep Nannapaneni et al.

Bayesian Networks (BN) are probabilistic graphical models that are widely used for uncertainty modeling, stochastic prediction and probabilistic inference. A Quantum Bayesian Network (QBN) is a quantum version of the Bayesian network that utilizes the principles of quantum mechanical systems to improve the computational performance of various analyses. In this paper, we experimentally evaluate the performance of QBN on various IBM QX hardware against Qiskit simulator and classical analysis. We consider a 4-node BN for stock prediction for our experimental evaluation. We construct a quantum circuit to represent the 4-node BN using Qiskit, and run the circuit on nine IBM quantum devices: Yorktown, Vigo, Ourense, Essex, Burlington, London, Rome, Athens and Melbourne. We will also compare the performance of each device across the four levels of optimization performed by the IBM Transpiler when mapping a given quantum circuit to a given device. We use the root mean square percentage error as the metric for performance comparison of various hardware.

Akshay Rangamani, Nam H. Nguyen, Abhishek Kumar et al.

It has been empirically observed that the flatness of minima obtained from training deep networks seems to correlate with better generalization. However, for deep networks with positively homogeneous activations, most measures of sharpness/flatness are not invariant to rescaling of the network parameters, corresponding to the same function. This means that the measure of flatness/sharpness can be made as small or as large as possible through rescaling, rendering the quantitative measures meaningless. In this paper we show that for deep networks with positively homogenous activations, these rescalings constitute equivalence relations, and that these equivalence relations induce a quotient manifold structure in the parameter space. Using this manifold structure and an appropriate metric, we propose a Hessian-based measure for flatness that is invariant to rescaling. We use this new measure to confirm the proposition that Large-Batch SGD minima are indeed sharper than Small-Batch SGD minima.

Lam M. Nguyen, Nam H. Nguyen, Dzung T. Phan et al.

In this paper, we consider a general stochastic optimization problem which is often at the core of supervised learning, such as deep learning and linear classification. We consider a standard stochastic gradient descent (SGD) method with a fixed, large step size and propose a novel assumption on the objective function, under which this method has the improved convergence rates (to a neighborhood of the optimal solutions). We then empirically demonstrate that these assumptions hold for logistic regression and standard deep neural networks on classical data sets. Thus our analysis helps to explain when efficient behavior can be expected from the SGD method in training classification models and deep neural networks.

Minh Dao, Nam H. Nguyen, Nasser M. Nasrabadi et al.

In this paper, we propose a general collaborative sparse representation framework for multi-sensor classification, which takes into account the correlations as well as complementary information between heterogeneous sensors simultaneously while considering joint sparsity within each sensor's observations. We also robustify our models to deal with the presence of sparse noise and low-rank interference signals. Specifically, we demonstrate that incorporating the noise or interference signal as a low-rank component in our models is essential in a multi-sensor classification problem when multiple co-located sources/sensors simultaneously record the same physical event. We further extend our frameworks to kernelized models which rely on sparsely representing a test sample in terms of all the training samples in a feature space induced by a kernel function. A fast and efficient algorithm based on alternative direction method is proposed where its convergence to an optimal solution is guaranteed. Extensive experiments are conducted on several real multi-sensor data sets and results are compared with the conventional classifiers to verify the effectiveness of the proposed methods.