SEARCH · Searcharxiv

Results for “transformer architecture”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 469 records · Page 26Linked to original sources

arXiv2024

A Survey on Structure-Preserving Graph Transformers

The transformer architecture has shown remarkable success in various domains, such as natural language processing and computer vision. When it comes to graph learning, transformers are required not only to capture the interactions between pairs of nodes but also to preserve graph structures connoting the underlying relations and proximity between them, showing the expressive power to capture different graph structures. Accordingly, various structure-preserving graph transformers have been proposed and widely used for various tasks, such as graph-level tasks in bioinformatics and chemoinformatics. However, strategies related to graph structure preservation have not been well organized and systematized in the literature. In this paper, we provide a comprehensive overview of structure-preserving graph transformers and generalize these methods from the perspective of their design objective. First, we divide strategies into four main groups: node feature modulation, context node sampling, graph rewriting, and transformer architecture improvements. We then further divide the strategies according to the coverage and goals of graph structure preservation. Furthermore, we also discuss challenges and future directions for graph transformer models to preserve the graph structure and understand the nature of graphs.

cs.LG↗

arXiv2023

Relphormer: Relational Graph Transformer for Knowledge Graph Representations

Transformers have achieved remarkable performance in widespread fields, including natural language processing, computer vision and graph mining. However, vanilla Transformer architectures have not yielded promising improvements in the Knowledge Graph (KG) representations, where the translational distance paradigm dominates this area. Note that vanilla Transformer architectures struggle to capture the intrinsically heterogeneous structural and semantic information of knowledge graphs. To this end, we propose a new variant of Transformer for knowledge graph representations dubbed Relphormer. Specifically, we introduce Triple2Seq which can dynamically sample contextualized sub-graph sequences as the input to alleviate the heterogeneity issue. We propose a novel structure-enhanced self-attention mechanism to encode the relational information and keep the semantic information within entities and relations. Moreover, we utilize masked knowledge modeling for general knowledge graph representation learning, which can be applied to various KG-based tasks including knowledge graph completion, question answering, and recommendation. Experimental results on six datasets show that Relphormer can obtain better performance compared with baselines. Code is available in https://github.com/zjunlp/Relphormer.

cs.CL↗

arXiv2024

Knowledge-enhanced Transformer for Multivariate Long Sequence Time-series Forecasting

Multivariate Long Sequence Time-series Forecasting (LSTF) has been a critical task across various real-world applications. Recent advancements focus on the application of transformer architectures attributable to their ability to capture temporal patterns effectively over extended periods. However, these approaches often overlook the inherent relationships and interactions between the input variables that could be drawn from their characteristic properties. In this paper, we aim to bridge this gap by integrating information-rich Knowledge Graph Embeddings (KGE) with state-of-the-art transformer-based architectures. We introduce a novel approach that encapsulates conceptual relationships among variables within a well-defined knowledge graph, forming dynamic and learnable KGEs for seamless integration into the transformer architecture. We investigate the influence of this integration into seminal architectures such as PatchTST, Autoformer, Informer, and Vanilla Transformer. Furthermore, we thoroughly investigate the performance of these knowledge-enhanced architectures along with their original implementations for long forecasting horizons and demonstrate significant improvement in the benchmark results. This enhancement empowers transformer-based architectures to address the inherent structural relation between variables. Our knowledge-enhanced approach improves the accuracy of multivariate LSTF by capturing complex temporal and relational dynamics across multiple domains. To substantiate the validity of our model, we conduct comprehensive experiments using Weather and Electric Transformer Temperature (ETT) datasets.

cs.LG↗

arXiv2024

Channel Boosted CNN-Transformer-based Multi-Level and Multi-Scale Nuclei Segmentation

Accurate nuclei segmentation is an essential foundation for various applications in computational pathology, including cancer diagnosis and treatment planning. Even slight variations in nuclei representations can significantly impact these downstream tasks. However, achieving accurate segmentation remains challenging due to factors like clustered nuclei, high intra-class variability in size and shape, resemblance to other cells, and color or contrast variations between nuclei and background. Despite the extensive utilization of Convolutional Neural Networks (CNNs) in medical image segmentation, they may have trouble capturing long-range dependencies crucial for accurate nuclei delineation. Transformers address this limitation but might miss essential low-level features. To overcome these limitations, we utilized CNN-Transformer-based techniques for nuclei segmentation in H&E stained histology images. In this work, we proposed two CNN-Transformer architectures, Nuclei Hybrid Vision Transformer (NucleiHVT) and Channel Boosted Nuclei Hybrid Vision Transformer (CB-NucleiHVT), that leverage the strengths of both CNNs and Transformers to effectively learn nuclei boundaries in multi-organ histology images. The first architecture, NucleiHVT is inspired by the UNet architecture and incorporates the dual attention mechanism to capture both multi-level and multi-scale context effectively. The CB-NucleiHVT network, on the other hand, utilizes the concept of channel boosting to learn diverse feature spaces, enhancing the model's ability to distinguish subtle variations in nuclei characteristics. Detailed evaluation of two medical image segmentation datasets shows that the proposed architectures outperform existing CNN-based, Transformer-based, and hybrid methods. The proposed networks demonstrated effective results both in terms of quantitative metrics, and qualitative visual assessment.

eess.IV↗

arXiv2022

Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention

Most of today's AI systems focus on using self-attention mechanisms and transformer architectures on large amounts of diverse data to achieve impressive performance gains. In this paper, we propose to augment the transformer architecture with an external attention mechanism to bring external knowledge and context to bear. By integrating external information into the prediction process, we hope to reduce the need for ever-larger models and increase the democratization of AI systems. We find that the proposed external attention mechanism can significantly improve the performance of existing AI systems, allowing practitioners to easily customize foundation AI models to many diverse downstream applications. In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities. The proposed system, Knowledgeable External Attention for commonsense Reasoning (KEAR), reaches human parity on the open CommonsenseQA research benchmark with an accuracy of 89.4\% in comparison to the human accuracy of 88.9\%.

cs.CL↗

arXiv2025

Leveraging Vision Transformers for Enhanced Classification of Emotions using ECG Signals

Biomedical signals provide insights into various conditions affecting the human body. Beyond diagnostic capabilities, these signals offer a deeper understanding of how specific organs respond to an individual's emotions and feelings. For instance, ECG data can reveal changes in heart rate variability linked to emotional arousal, stress levels, and autonomic nervous system activity. This data offers a window into the physiological basis of our emotional states. Recent advancements in the field diverge from conventional approaches by leveraging the power of advanced transformer architectures, which surpass traditional machine learning and deep learning methods. We begin by assessing the effectiveness of the Vision Transformer (ViT), a forefront model in image classification, for identifying emotions in imaged ECGs. Following this, we present and evaluate an improved version of ViT, integrating both CNN and SE blocks, aiming to bolster performance on imaged ECGs associated with emotion detection. Our method unfolds in two critical phases: first, we apply advanced preprocessing techniques for signal purification and converting signals into interpretable images using continuous wavelet transform and power spectral density analysis; second, we unveil a performance-boosted vision transformer architecture, cleverly enhanced with convolutional neural network components, to adeptly tackle the challenges of emotion recognition. Our methodology's robustness and innovation were thoroughly tested using ECG data from the YAAD and DREAMER datasets, leading to remarkable outcomes. For the YAAD dataset, our approach outperformed existing state-of-the-art methods in classifying seven unique emotional states, as well as in valence and arousal classification. Similarly, in the DREAMER dataset, our method excelled in distinguishing between valence, arousal and dominance, surpassing current leading techniques.

eess.SP↗

arXiv2025

IVE: Enhanced Probabilistic Forecasting of Intraday Volume Ratio with Transformers

This paper presents a new approach to volume ratio prediction in financial markets, specifically targeting the execution of Volume-Weighted Average Price (VWAP) strategies. Recognizing the importance of accurate volume profile forecasting, our research leverages the Transformer architecture to predict intraday volume ratio at a one-minute scale. We diverge from prior models that use log-transformed volume or turnover rates, instead opting for a prediction model that accounts for the intraday volume ratio's high variability, stabilized via log-normal transformation. Our input data incorporates not only the statistical properties of volume but also external volume-related features, absolute time information, and stock-specific characteristics to enhance prediction accuracy. The model structure includes an encoder-decoder Transformer architecture with a distribution head for greedy sampling, optimizing performance on high-liquidity stocks across both Korean and American markets. We extend the capabilities of our model beyond point prediction by introducing probabilistic forecasting that captures the mean and standard deviation of volume ratios, enabling the anticipation of significant intraday volume spikes. Furthermore, an agent with a simple trading logic demonstrates the practical application of our model through live trading tests in the Korean market, outperforming VWAP benchmarks over a period of two and a half months. Our findings underscore the potential of Transformer-based probabilistic models for volume ratio prediction and pave the way for future research advancements in this domain.

q-fin.CP↗

arXiv2021

Estimating articulatory movements in speech production with transformer networks

We estimate articulatory movements in speech production from different modalities - acoustics and phonemes. Acoustic-to articulatory inversion (AAI) is a sequence-to-sequence task. On the other hand, phoneme to articulatory (PTA) motion estimation faces a key challenge in reliably aligning the text and the articulatory movements. To address this challenge, we explore the use of a transformer architecture - FastSpeech, with explicit duration modelling to learn hard alignments between the phonemes and articulatory movements. We also train a transformer model on AAI. We use correlation coefficient (CC) and root mean squared error (rMSE) to assess the estimation performance in comparison to existing methods on both tasks. We observe 154%, 11.8% & 4.8% relative improvement in CC with subject-dependent, pooled and fine-tuning strategies, respectively, for PTA estimation. Additionally, on the AAI task, we obtain 1.5%, 3% and 3.1% relative gain in CC on the same setups compared to the state-of-the-art baseline. We further present the computational benefits of having transformer architecture as representation blocks.

eess.AS↗

arXiv2024

A Foundation Model for Soccer

We propose a foundation model for soccer, which is able to predict subsequent actions in a soccer match from a given input sequence of actions. As a proof of concept, we train a transformer architecture on three seasons of data from a professional soccer league. We quantitatively and qualitatively compare the performance of this transformer architecture to two baseline models: a Markov model and a multi-layer perceptron. Additionally, we discuss potential applications of our model. We provide an open-source implementation of our methods at https://github.com/danielhocevar/Foundation-Model-for-Soccer.

cs.LG↗

arXiv2025

Transformer representation learning is necessary for dynamic multi-modal physiological data on small-cohort patients

Postoperative delirium (POD), a severe neuropsychiatric complication affecting nearly 50% of high-risk surgical patients, is defined as an acute disorder of attention and cognition, It remains significantly underdiagnosed in the intensive care units (ICUs) due to subjective monitoring methods. Early and accurate diagnosis of POD is critical and achievable. Here, we propose a POD prediction framework comprising a Transformer representation model followed by traditional machine learning algorithms. Our approaches utilizes multi-modal physiological data, including amplitude-integrated electroencephalography (aEEG), vital signs, electrocardiographic monitor data as well as hemodynamic parameters. We curated the first multi-modal POD dataset encompassing two patient types and evaluated the various Transformer architectures for representation learning. Empirical results indicate a consistent improvements of sensitivity and Youden index in patient TYPE I using Transformer representations, particularly our fusion adaptation of Pathformer. By enabling effective delirium diagnosis from postoperative day 1 to 3, our extensive experimental findings emphasize the potential of multi-modal physiological data and highlight the necessity of representation learning via multi-modal Transformer architecture in clinical diagnosis.

cs.LG↗

arXiv2021

Incorporating Convolution Designs into Visual Transformers

Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. However, pure Transformer architectures often require a large amount of training data or extra supervision to obtain comparable performance with convolutional neural networks (CNNs). To overcome these limitations, we analyze the potential drawbacks when directly borrowing Transformer architectures from NLP. Then we propose a new \textbf{Convolution-enhanced image Transformer (CeiT)} which combines the advantages of CNNs in extracting low-level features, strengthening locality, and the advantages of Transformers in establishing long-range dependencies. Three modifications are made to the original Transformer: \textbf{1)} instead of the straightforward tokenization from raw input images, we design an \textbf{Image-to-Tokens (I2T)} module that extracts patches from generated low-level features; \textbf{2)} the feed-froward network in each encoder block is replaced with a \textbf{Locally-enhanced Feed-Forward (LeFF)} layer that promotes the correlation among neighboring tokens in the spatial dimension; \textbf{3)} a \textbf{Layer-wise Class token Attention (LCA)} is attached at the top of the Transformer that utilizes the multi-level representations. Experimental results on ImageNet and seven downstream tasks show the effectiveness and generalization ability of CeiT compared with previous Transformers and state-of-the-art CNNs, without requiring a large amount of training data and extra CNN teachers. Besides, CeiT models also demonstrate better convergence with $3\times$ fewer training iterations, which can reduce the training cost significantly\footnote{Code and models will be released upon acceptance.}.

cs.CV↗

arXiv2026

Recursive transformers for semiconductor thermo-mechanical reliability

Transformer-based surrogate models are increasingly used to replace expensive first-principles simulation in engineering design. But conventional transformer architectures are often over parameterized for the small, low-dimensional datasets typical of engineering design spaces, where large simulation data is expensive to generate. Under these conditions, excess parameter capacity leads to overfitting rather than improved accuracy, while also incurring unnecessary memory and compute overhead. This motivates a shift towards architectures that focus on additional compute rather than additional learnable parameters. This paper presents a hardware-aware evaluation of three recursive transformer paradigms for surrogate thermo-mechanical analysis of advanced packages: a)Tiny Recursive Model, b) our proposed Depth Recursive transformer, c) and a simple recursive transformer. We systematically compare their predictive performance (Recall, Mean Reciprocal Rank), parameter count, computational complexity (FLOPs), providing practical design guidelines for selecting recursive transformer architectures under resource-constrained scenarios. We validate this principle on two low-dimensional engineering prediction tasks: 1) thermo-mechanical reliability analysis of advanced semiconductor packages, where stress and warpage from thermal cycling must be evaluated repeatedly across a design-of-experiments sweep under costly finite element analysis (FEA). 2) Laplace PDE iterative numerical solver for capacitance field. Overall, recursive weight-sharing transformers provide an effective and generalizable trade-off between prediction accuracy, parameter efficiency, and computational cost for small data engineering surrogate modeling.

cs.LG↗

arXiv2022

Relaxed Attention for Transformer Models

The powerful modeling capabilities of all-attention-based transformer architectures often cause overfitting and - for natural language processing tasks - lead to an implicitly learned internal language model in the autoregressive transformer decoder complicating the integration of external language models. In this paper, we explore relaxed attention, a simple and easy-to-implement smoothing of the attention weights, yielding a two-fold improvement to the general transformer architecture: First, relaxed attention provides regularization when applied to the self-attention layers in the encoder. Second, we show that it naturally supports the integration of an external language model as it suppresses the implicitly learned internal language model by relaxing the cross attention in the decoder. We demonstrate the benefit of relaxed attention across several tasks with clear improvement in combination with recent benchmark approaches. Specifically, we exceed the former state-of-the-art performance of 26.90% word error rate on the largest public lip-reading LRS3 benchmark with a word error rate of 26.31%, as well as we achieve a top-performing BLEU score of 37.67 on the IWSLT14 (DE$\rightarrow$EN) machine translation task without external language models and virtually no additional model parameters. Code and models will be made publicly available.

cs.LG↗

arXiv2025

DeepKoopFormer: A Koopman Enhanced Transformer Based Architecture for Time Series Forecasting

Time series forecasting plays a vital role across scientific, industrial, and environmental domains, especially when dealing with high-dimensional and nonlinear systems. While Transformer-based models have recently achieved state-of-the-art performance in long-range forecasting, they often suffer from interpretability issues and instability in the presence of noise or dynamical uncertainty. In this work, we propose DeepKoopFormer, a principled forecasting framework that combines the representational power of Transformers with the theoretical rigor of Koopman operator theory. Our model features a modular encoder-propagator-decoder structure, where temporal dynamics are learned via a spectrally constrained, linear Koopman operator in a latent space. We impose structural guarantees-such as bounded spectral radius, Lyapunov based energy regularization, and orthogonal parameterization to ensure stability and interpretability. Comprehensive evaluations are conducted on both synthetic dynamical systems, real-world climate dataset (wind speed and surface pressure), financial time series (cryptocurrency), and electricity generation dataset using the Python package that is prepared for this purpose. Across all experiments, DeepKoopFormer consistently outperforms standard LSTM and baseline Transformer models in terms of accuracy, robustness to noise, and long-term forecasting stability. These results establish DeepKoopFormer as a flexible, interpretable, and robust framework for forecasting in high dimensional and dynamical settings.

cs.LG↗

arXiv2025

Kolmogorov GAM Networks are all you need!

Kolmogorov GAM (K-GAM) networks are shown to be an efficient architecture for training and inference. They are an additive model with an embedding that is independent of the function of interest. They provide an alternative to the transformer architecture. They are the machine learning version of Kolmogorov's Superposition Theorem (KST) which provides an efficient representations of a multivariate function. Such representations have use in machine learning for encoding dictionaries (a.k.a. "look-up" tables). KST theory also provides a representation based on translates of the Köppen function. The goal of our paper is to interpret this representation in a machine learning context for applications in Artificial Intelligence (AI). Our architecture is equivalent to a topological embedding which is independent of the function together with an additive layer that uses a Generalized Additive Model (GAM). This provides a class of learning procedures with far fewer parameters than current deep learning algorithms. Implementation can be parallelizable which makes our algorithms computationally attractive. To illustrate our methodology, we use the Iris data from statistical learning. We also show that our additive model with non-linear embedding provides an alternative to transformer architectures which from a statistical viewpoint are kernel smoothers. Additive KAN models therefore provide a natural alternative to transformers. Finally, we conclude with directions for future research.

cs.LG↗

arXiv2022

A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation

BERT4Rec is an effective model for sequential recommendation based on the Transformer architecture. In the original publication, BERT4Rec claimed superiority over other available sequential recommendation approaches (e.g. SASRec), and it is now frequently being used as a state-of-the art baseline for sequential recommendations. However, not all subsequent publications confirmed this result and proposed other models that were shown to outperform BERT4Rec in effectiveness. In this paper we systematically review all publications that compare BERT4Rec with another popular Transformer-based model, namely SASRec, and show that BERT4Rec results are not consistent within these publications. To understand the reasons behind this inconsistency, we analyse the available implementations of BERT4Rec and show that we fail to reproduce results of the original BERT4Rec publication when using their default configuration parameters. However, we are able to replicate the reported results with the original code if training for a much longer amount of time (up to 30x) compared to the default configuration. We also propose our own implementation of BERT4Rec based on the Hugging Face Transformers library, which we demonstrate replicates the originally reported results on 3 out 4 datasets, while requiring up to 95% less training time to converge. Overall, from our systematic review and detailed experiments, we conclude that BERT4Rec does indeed exhibit state-of-the-art effectiveness for sequential recommendation, but only when trained for a sufficient amount of time. Additionally, we show that our implementation can further benefit from adapting other Transformer architectures that are available in the Hugging Face Transformers library (e.g. using disentangled attention, as provided by DeBERTa, or larger hidden layer size cf. ALBERT).

cs.IR↗

arXiv2024

LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation

UNet and its variants have been widely used in medical image segmentation. However, these models, especially those based on Transformer architectures, pose challenges due to their large number of parameters and computational loads, making them unsuitable for mobile health applications. Recently, State Space Models (SSMs), exemplified by Mamba, have emerged as competitive alternatives to CNN and Transformer architectures. Building upon this, we employ Mamba as a lightweight substitute for CNN and Transformer within UNet, aiming at tackling challenges stemming from computational resource limitations in real medical settings. To this end, we introduce the Lightweight Mamba UNet (LightM-UNet) that integrates Mamba and UNet in a lightweight framework. Specifically, LightM-UNet leverages the Residual Vision Mamba Layer in a pure Mamba fashion to extract deep semantic features and model long-range spatial dependencies, with linear computational complexity. Extensive experiments conducted on two real-world 2D/3D datasets demonstrate that LightM-UNet surpasses existing state-of-the-art literature. Notably, when compared to the renowned nnU-Net, LightM-UNet achieves superior segmentation performance while drastically reducing parameter and computation costs by 116x and 21x, respectively. This highlights the potential of Mamba in facilitating model lightweighting. Our code implementation is publicly available at https://github.com/MrBlankness/LightM-UNet.

eess.IV↗

arXiv2024

Inference Optimization of Foundation Models on AI Accelerators

Powerful foundation models, including large language models (LLMs), with Transformer architectures have ushered in a new era of Generative AI across various industries. Industry and research community have witnessed a large number of new applications, based on those foundation models. Such applications include question and answer, customer services, image and video generation, and code completions, among others. However, as the number of model parameters reaches to hundreds of billions, their deployment incurs prohibitive inference costs and high latency in real-world scenarios. As a result, the demand for cost-effective and fast inference using AI accelerators is ever more higher. To this end, our tutorial offers a comprehensive discussion on complementary inference optimization techniques using AI accelerators. Beginning with an overview of basic Transformer architectures and deep learning system frameworks, we deep dive into system optimization techniques for fast and memory-efficient attention computations and discuss how they can be implemented efficiently on AI accelerators. Next, we describe architectural elements that are key for fast transformer inference. Finally, we examine various model compression and fast decoding strategies in the same context.

cs.AI↗