TS-TCD: Triplet-Level Cross-Modal Distillation for Time-Series Forecasting Using Large Language Models

• URL: http://arxiv.org/abs/2409.14978v1
• Date: Mon, 23 Sep 2024 12:57:24 GMT
• Title: TS-TCD: Triplet-Level Cross-Modal Distillation for Time-Series Forecasting Using Large Language Models
• Authors: Pengfei Wang, Huanran Zheng, Silong Dai, Wenjing Yue, Wei Zhu, Xiaoling Wang,
• Abstract summary: We present a novel framework, TS-TCD, which introduces a comprehensive three-tiered cross-modal knowledge distillation mechanism. Unlike prior work that focuses on isolated alignment techniques, our framework systematically integrates. Experiments on benchmark time-series demonstrate that TS-TCD achieves state-of-the-art results, outperforming traditional methods in both accuracy and robustness.
• Score: 15.266543423942617
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, large language models (LLMs) have shown great potential in time-series analysis by capturing complex dependencies and improving predictive performance. However, existing approaches often struggle with modality alignment, leading to suboptimal results. To address these challenges, we present a novel framework, TS-TCD, which introduces a comprehensive three-tiered cross-modal knowledge distillation mechanism. Unlike prior work that focuses on isolated alignment techniques, our framework systematically integrates: 1) Dynamic Adaptive Gating for Input Encoding and Alignment}, ensuring coherent alignment between time-series tokens and QR-decomposed textual embeddings; 2) Layer-Wise Contrastive Learning}, aligning intermediate representations across modalities to reduce feature-level discrepancies; and 3) Optimal Transport-Driven Output Alignment}, which ensures consistent output predictions through fine-grained cross-modal alignment. Extensive experiments on benchmark time-series datasets demonstrate that TS-TCD achieves state-of-the-art results, outperforming traditional methods in both accuracy and robustness.

Related papers

• Enhancing Time Series Forecasting via Multi-Level Text Alignment with LLMs [6.612196783595362]
  We propose a multi-level text alignment framework for time series forecasting using large language models (LLMs) Our method decomposes time series into trend, seasonal, and residual components, which are then reprogrammed into component-specific text representations. Experiments on multiple datasets demonstrate that our method outperforms state-of-the-art models in accuracy while providing good interpretability.
  arXiv  Detail & Related papers  (2025-04-10T01:02:37Z)
• Detecting Document-level Paraphrased Machine Generated Content: Mimicking Human Writing Style and Involving Discourse Features [57.34477506004105]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation. We introduce novel methodologies and datasets to overcome these challenges. We propose MhBART, an encoder-decoder model designed to emulate human writing style. We also propose DTransformer, a model that integrates discourse analysis through PDTB preprocessing to encode structural features.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• Text2Freq: Learning Series Patterns from Text via Frequency Domain [8.922661807801227]
  Text2Freq is a cross-modality model that integrates text and time series data via the frequency domain. Our experiments on paired datasets of real-world stock prices and synthetic texts show that Text2Freq achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-01T16:11:02Z)
• Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting [26.141054975797868]
  We propose a novel Adaptive Multi-Scale Decomposition (AMD) framework for time series forecasting (TSF) Our framework decomposes time series into distinct temporal patterns at multiple scales, leveraging the Multi-Scale Decomposable Mixing (MDM) block. Our approach effectively models both temporal and channel dependencies and utilizes autocorrelation to refine multi-scale data integration.
  arXiv  Detail & Related papers  (2024-06-06T05:27:33Z)
• Towards Robustness of Text-to-Visualization Translation against Lexical and Phrasal Variability [27.16741353384065]
  Text-to-vis models often rely on lexical matching between words in the questions and tokens in data schemas. In this study, we examine the robustness of current text-to-vis models, an area that has not previously been explored. We propose a novel framework based on Retrieval-Augmented Generation (RAG) technique, named GRED, specifically designed to address input perturbations in two variants.
  arXiv  Detail & Related papers  (2024-04-10T16:12:50Z)
• Sequential Visual and Semantic Consistency for Semi-supervised Text Recognition [56.968108142307976]
  Scene text recognition (STR) is a challenging task that requires large-scale annotated data for training. Most existing STR methods resort to synthetic data, which may introduce domain discrepancy and degrade the performance of STR models. This paper proposes a novel semi-supervised learning method for STR that incorporates word-level consistency regularization from both visual and semantic aspects.
  arXiv  Detail & Related papers  (2024-02-24T13:00:54Z)
• Recurrent Alignment with Hard Attention for Hierarchical Text Rating [6.858867989434858]
  We propose a novel framework for hierarchical text rating utilizing large language models (LLMs) Our framework incorporates Recurrent Alignment with Hard Attention (RAHA) Experimental results demonstrate that RAHA outperforms existing state-of-the-art methods on three hierarchical text rating datasets.
  arXiv  Detail & Related papers  (2024-02-14T00:40:51Z)
• AToM: Amortized Text-to-Mesh using 2D Diffusion [107.02696990299032]
  Amortized Text-to-Mesh (AToM) is a feed-forward framework optimized across multiple text prompts simultaneously. AToM directly generates high-quality textured meshes in less than 1 second with around 10 times reduction in the training cost. AToM significantly outperforms state-of-the-art amortized approaches with over 4 times higher accuracy.
  arXiv  Detail & Related papers  (2024-02-01T18:59:56Z)
• Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning [7.4106801792345705]
  We propose DE-TSMCL, an innovative distillation enhanced framework for long sequence time series forecasting. Specifically, we design a learnable data augmentation mechanism which adaptively learns whether to mask a timestamp. Then, we propose a contrastive learning task with momentum update to explore inter-sample and intra-temporal correlations of time series. By developing model loss from multiple tasks, we can learn effective representations for downstream forecasting task.
  arXiv  Detail & Related papers  (2024-01-31T12:52:10Z)
• Mlinear: Rethink the Linear Model for Time-series Forecasting [9.841293660201261]
  Mlinear is a simple yet effective method based mainly on linear layers. We introduce a new loss function that significantly outperforms the widely used mean squared error (MSE) on multiple datasets. Our method significantly outperforms PatchTST with a ratio of 21:3 at 336 sequence length input and 29:10 at 512 sequence length input.
  arXiv  Detail & Related papers  (2023-05-08T15:54:18Z)
• Multi-Modal Continual Test-Time Adaptation for 3D Semantic Segmentation [26.674085603033742]
  Continual Test-Time Adaptation (CTTA) generalizes conventional Test-Time Adaptation (TTA) by assuming that the target domain is dynamic over time rather than stationary. In this paper, we explore Multi-Modal Continual Test-Time Adaptation (MM-CTTA) as a new extension of CTTA for 3D semantic segmentation.
  arXiv  Detail & Related papers  (2023-03-18T16:51:19Z)
• Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning [53.68371566336254]
  We argue that the key to better performance lies in meaningful latent modality structures instead of perfect modality alignment. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization.
  arXiv  Detail & Related papers  (2023-03-10T14:38:49Z)
• Gait Recognition in the Wild with Multi-hop Temporal Switch [81.35245014397759]
  gait recognition in the wild is a more practical problem that has attracted the attention of the community of multimedia and computer vision. This paper presents a novel multi-hop temporal switch method to achieve effective temporal modeling of gait patterns in real-world scenes.
  arXiv  Detail & Related papers  (2022-09-01T10:46:09Z)
• Text Revision by On-the-Fly Representation Optimization [76.11035270753757]
  Current state-of-the-art methods formulate these tasks as sequence-to-sequence learning problems. We present an iterative in-place editing approach for text revision, which requires no parallel data. It achieves competitive and even better performance than state-of-the-art supervised methods on text simplification.
  arXiv  Detail & Related papers  (2022-04-15T07:38:08Z)
• Data-to-text Generation with Variational Sequential Planning [74.3955521225497]
  We consider the task of data-to-text generation, which aims to create textual output from non-linguistic input. We propose a neural model enhanced with a planning component responsible for organizing high-level information in a coherent and meaningful way. We infer latent plans sequentially with a structured variational model, while interleaving the steps of planning and generation.
  arXiv  Detail & Related papers  (2022-02-28T13:17:59Z)
• Contrastive predictive coding for Anomaly Detection in Multi-variate Time Series Data [6.463941665276371]
  We propose a Time-series Representational Learning through Contrastive Predictive Coding (TRL-CPC) towards anomaly detection in MVTS data. First, we jointly optimize an encoder, an auto-regressor and a non-linear transformation function to effectively learn the representations of the MVTS data sets.
  arXiv  Detail & Related papers  (2022-02-08T04:25:29Z)
• Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding [53.377028000325424]
  We propose an Iterative Alignment Network (IA-Net) for temporal sentence grounding task. We pad multi-modal features with learnable parameters to alleviate the nowhere-to-attend problem of non-matched frame-word pairs. We also devise a calibration module following each attention module to refine the alignment knowledge.
  arXiv  Detail & Related papers  (2021-09-14T02:08:23Z)
• AGGGEN: Ordering and Aggregating while Generating [12.845842212733695]
  We present AGGGEN, a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems. AGGGEN performs sentence planning at the same time as generating text by learning latent alignments between input representation and target text.
  arXiv  Detail & Related papers  (2021-06-10T08:14:59Z)
• Self-Supervised Multi-Frame Monocular Scene Flow [61.588808225321735]
  We introduce a multi-frame monocular scene flow network based on self-supervised learning. We observe state-of-the-art accuracy among monocular scene flow methods based on self-supervised learning.
  arXiv  Detail & Related papers  (2021-05-05T17:49:55Z)
• Consistency Guided Scene Flow Estimation [159.24395181068218]
  CGSF is a self-supervised framework for the joint reconstruction of 3D scene structure and motion from stereo video. We show that the proposed model can reliably predict disparity and scene flow in challenging imagery. It achieves better generalization than the state-of-the-art, and adapts quickly and robustly to unseen domains.
  arXiv  Detail & Related papers  (2020-06-19T17:28:07Z)
• POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training [93.79766670391618]
  We present POINTER, a novel insertion-based approach for hard-constrained text generation. The proposed method operates by progressively inserting new tokens between existing tokens in a parallel manner. The resulting coarse-to-fine hierarchy makes the generation process intuitive and interpretable.
  arXiv  Detail & Related papers  (2020-05-01T18:11:54Z)
• Bottom-Up Temporal Action Localization with Mutual Regularization [107.39785866001868]
  State-of-the-art solutions for TAL involve evaluating the frame-level probabilities of three action-indicating phases. We introduce two regularization terms to mutually regularize the learning procedure. Experiments are performed on two popular TAL datasets, THUMOS14 and ActivityNet1.3.
  arXiv  Detail & Related papers  (2020-02-18T03:59:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.