Sampling Foundational Transformer: A Theoretical Perspective

• URL: http://arxiv.org/abs/2408.05822v2
• Date: Sat, 17 Aug 2024 22:33:06 GMT
• Title: Sampling Foundational Transformer: A Theoretical Perspective
• Authors: Viet Anh Nguyen, Minh Lenhat, Khoa Nguyen, Duong Duc Hieu, Dao Huu Hung, Truong Son Hy,
• Abstract summary: We propose Foundational Sampling Transformer (SFT) that can work on multiple data modalities. SFT has achieved competitive results on many benchmarks, while being faster in inference, compared to other very specialized models.
• Score: 12.7600763629179
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and difficulty of training. To apply transformers across different data modalities, practitioners have to make specific clever data-modality-dependent constructions. In this paper, we propose Sampling Foundational Transformer (SFT) that can work on multiple data modalities (e.g., point cloud, graph, and sequence) and constraints (e.g., rotational-invariant). The existence of such model is important as contemporary foundational modeling requires operability on multiple data sources. For efficiency on large number of tokens, our model relies on our context aware sampling-without-replacement mechanism for both linear asymptotic computational complexity and real inference time gain. For efficiency, we rely on our newly discovered pseudoconvex formulation of transformer layer to increase model's convergence rate. As a model working on multiple data modalities, SFT has achieved competitive results on many benchmarks, while being faster in inference, compared to other very specialized models.

Related papers

• SAMSA: Efficient Transformer for Many Data Modalities [12.7600763629179]
  We propose SAMSA - SAMpling-Self-Attention, a context-aware linear complexity self-attention mechanism. Our mechanism is based on a differentiable sampling without replacement method we discovered. SAMSA achieved competitive or even SOTA results on many benchmarks, while being faster in inference, compared to other very specialized models.
  arXiv  Detail & Related papers  (2024-08-10T00:09:06Z)
• UniTST: Effectively Modeling Inter-Series and Intra-Series Dependencies for Multivariate Time Series Forecasting [98.12558945781693]
  We propose a transformer-based model UniTST containing a unified attention mechanism on the flattened patch tokens. Although our proposed model employs a simple architecture, it offers compelling performance as shown in our experiments on several datasets for time series forecasting.
  arXiv  Detail & Related papers  (2024-06-07T14:39:28Z)
• Latent variable model for high-dimensional point process with structured missingness [4.451479907610764]
  Longitudinal data are important in numerous fields, such as healthcare, sociology and seismology. Real-world datasets can be high-dimensional, contain structured missingness patterns, and measurement time points can be governed by an unknown process. We propose a flexible and efficient latent-variable model that is capable of addressing all these limitations.
  arXiv  Detail & Related papers  (2024-02-08T15:41:48Z)
• Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection [88.23337313766353]
  This work first provides a comprehensive statistical theory for transformers to perform ICL. We show that transformers can implement a broad class of standard machine learning algorithms in context. A emphsingle transformer can adaptively select different base ICL algorithms.
  arXiv  Detail & Related papers  (2023-06-07T17:59:31Z)
• VTAE: Variational Transformer Autoencoder with Manifolds Learning [144.0546653941249]
  Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables. The nonlinearity of the generator implies that the latent space shows an unsatisfactory projection of the data space, which results in poor representation learning. We show that geodesics and accurate computation can substantially improve the performance of deep generative models.
  arXiv  Detail & Related papers  (2023-04-03T13:13:19Z)
• DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion [66.21290235237808]
  We introduce an energy constrained diffusion model which encodes a batch of instances from a dataset into evolutionary states. We provide rigorous theory that implies closed-form optimal estimates for the pairwise diffusion strength among arbitrary instance pairs. Experiments highlight the wide applicability of our model as a general-purpose encoder backbone with superior performance in various tasks.
  arXiv  Detail & Related papers  (2023-01-23T15:18:54Z)
• Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution [57.71199089609161]
  Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational self-attention mechanism. We propose an efficient Transformerbased model, named Conformer, which differentiates itself from existing methods for LTTF in three aspects.
  arXiv  Detail & Related papers  (2023-01-05T13:59:29Z)
• Robust representations of oil wells' intervals via sparse attention mechanism [2.604557228169423]
  We introduce the class of efficient Transformers named Regularized Transformers (Reguformers) The focus in our experiments is on oil&gas data, namely, well logs. To evaluate our models for such problems, we work with an industry-scale open dataset consisting of well logs of more than 20 wells.
  arXiv  Detail & Related papers  (2022-12-29T09:56:33Z)
• Scalable Gaussian Processes for Data-Driven Design using Big Data with Categorical Factors [14.337297795182181]
  Gaussian processes (GP) have difficulties in accommodating big datasets, categorical inputs, and multiple responses. We propose a GP model that utilizes latent variables and functions obtained through variational inference to address the aforementioned challenges simultaneously. Our approach is demonstrated for machine learning of ternary oxide materials and topology optimization of a multiscale compliant mechanism.
  arXiv  Detail & Related papers  (2021-06-26T02:17:23Z)
• A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning [34.90240171916858]
  We develop an efficient variational Bayes inference technique for infinite mixtures of probabilistic local models. We highlight the model's power in combining data-driven adaptation, fast prediction and the ability to deal with discontinuous functions and heteroscedastic noise. We use the learned models for online dynamics control of a Barrett-WAM manipulator, significantly improving the trajectory tracking performance.
  arXiv  Detail & Related papers  (2020-11-10T16:15:13Z)
• Transformer Hawkes Process [79.16290557505211]
  We propose a Transformer Hawkes Process (THP) model, which leverages the self-attention mechanism to capture long-term dependencies. THP outperforms existing models in terms of both likelihood and event prediction accuracy by a notable margin. We provide a concrete example, where THP achieves improved prediction performance for learning multiple point processes when incorporating their relational information.
  arXiv  Detail & Related papers  (2020-02-21T13:48:13Z)

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.