Coordinate In and Value Out: Training Flow Transformers in Ambient Space

• URL: http://arxiv.org/abs/2412.03791v1
• Date: Thu, 05 Dec 2024 01:00:07 GMT
• Title: Coordinate In and Value Out: Training Flow Transformers in Ambient Space
• Authors: Yuyang Wang, Anurag Ranjan, Josh Susskind, Miguel Angel Bautista,
• Abstract summary: Ambient Space Flow Transformers (ASFT) is a domain-agnostic approach to learn flow matching transformers in ambient space.<n>We introduce a conditionally independent point-wise training objective that enables ASFT to make predictions continuously in coordinate space.
• Score: 6.911507447184487
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flow matching models have emerged as a powerful method for generative modeling on domains like images or videos, and even on unstructured data like 3D point clouds. These models are commonly trained in two stages: first, a data compressor (i.e., a variational auto-encoder) is trained, and in a subsequent training stage a flow matching generative model is trained in the low-dimensional latent space of the data compressor. This two stage paradigm adds complexity to the overall training recipe and sets obstacles for unifying models across data domains, as specific data compressors are used for different data modalities. To this end, we introduce Ambient Space Flow Transformers (ASFT), a domain-agnostic approach to learn flow matching transformers in ambient space, sidestepping the requirement of training compressors and simplifying the training process. We introduce a conditionally independent point-wise training objective that enables ASFT to make predictions continuously in coordinate space. Our empirical results demonstrate that using general purpose transformer blocks, ASFT effectively handles different data modalities such as images and 3D point clouds, achieving strong performance in both domains and outperforming comparable approaches. ASFT is a promising step towards domain-agnostic flow matching generative models that can be trivially adopted in different data domains.

Related papers

• Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models [0.0]
  This work proposes a 3 Phase technique to adjust a base model for a classification task. We adapt the model's signal to the data distribution by performing further training with a Denoising Autoencoder (DAE) In addition, we introduce a new data augmentation approach for Supervised Contrastive Learning to correct the unbalanced datasets.
  arXiv  Detail & Related papers  (2024-05-23T11:08:35Z)
• Heterogeneous Federated Learning with Splited Language Model [22.65325348176366]
  Federated Split Learning (FSL) is a promising distributed learning paradigm in practice. In this paper, we harness Pre-trained Image Transformers (PITs) as the initial model, coined FedV, to accelerate the training process and improve model robustness. We are the first to provide a systematic evaluation of FSL methods with PITs in real-world datasets, different partial device participations, and heterogeneous data splits.
  arXiv  Detail & Related papers  (2024-03-24T07:33:08Z)
• In-Context Convergence of Transformers [63.04956160537308]
  We study the learning dynamics of a one-layer transformer with softmax attention trained via gradient descent. For data with imbalanced features, we show that the learning dynamics take a stage-wise convergence process.
  arXiv  Detail & Related papers  (2023-10-08T17:55:33Z)
• Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification [10.291631977766672]
  We propose a novel approach called Fourier Test-time Adaptation (FTTA) to integrate input and model tuning. FTTA builds a reliable multi-level consistency measurement of paired inputs for achieving self-supervised of prediction. It was extensively validated on three large classification datasets with different modalities and organs.
  arXiv  Detail & Related papers  (2023-06-05T02:29:38Z)
• Emergent Agentic Transformer from Chain of Hindsight Experience [96.56164427726203]
  We show that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches. This is the first time that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches.
  arXiv  Detail & Related papers  (2023-05-26T00:43:02Z)
• Adapting Sentence Transformers for the Aviation Domain [0.8437187555622164]
  We propose a novel approach for adapting sentence transformers for the aviation domain. Our method is a two-stage process consisting of pre-training followed by fine-tuning. Our work highlights the importance of domain-specific adaptation in developing high-quality NLP solutions for specialized industries like aviation.
  arXiv  Detail & Related papers  (2023-05-16T15:53:24Z)
• AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation [80.33846577924363]
  We present All-Pairs Multi-Field Transforms (AMT), a new network architecture for video framegithub. It is based on two essential designs. First, we build bidirectional volumes for all pairs of pixels, and use the predicted bilateral flows to retrieve correlations. Second, we derive multiple groups of fine-grained flow fields from one pair of updated coarse flows for performing backward warping on the input frames separately.
  arXiv  Detail & Related papers  (2023-04-19T16:18:47Z)
• Transformers for End-to-End InfoSec Tasks: A Feasibility Study [6.847381178288385]
  We implement transformer models for two distinct InfoSec data formats - specifically URLs and PE files. We show that our URL transformer model requires a different training approach to reach high performance levels. We demonstrate that this approach performs comparably to well-established malware detection models on benchmark PE file datasets.
  arXiv  Detail & Related papers  (2022-12-05T23:50:46Z)
• Inference from Real-World Sparse Measurements [21.194357028394226]
  Real-world problems often involve complex and unstructured sets of measurements, which occur when sensors are sparsely placed in either space or time. Deep learning architectures capable of processing sets of measurements with positions varying from set to set and extracting readouts anywhere are methodologically difficult. We propose an attention-based model focused on applicability and practical robustness, with two key design contributions.
  arXiv  Detail & Related papers  (2022-10-20T13:42:20Z)
• Parallel Successive Learning for Dynamic Distributed Model Training over Heterogeneous Wireless Networks [50.68446003616802]
  Federated learning (FedL) has emerged as a popular technique for distributing model training over a set of wireless devices. We develop parallel successive learning (PSL), which expands the FedL architecture along three dimensions. Our analysis sheds light on the notion of cold vs. warmed up models, and model inertia in distributed machine learning.
  arXiv  Detail & Related papers  (2022-02-07T05:11:01Z)
• Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks [75.69896269357005]
  Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. In this paper, we explore how to apply mixup to natural language processing tasks. We incorporate mixup to transformer-based pre-trained architecture, named "mixup-transformer", for a wide range of NLP tasks.
  arXiv  Detail & Related papers  (2020-10-05T23:37:30Z)
• Pre-Trained Models for Heterogeneous Information Networks [57.78194356302626]
  We propose a self-supervised pre-training and fine-tuning framework, PF-HIN, to capture the features of a heterogeneous information network. PF-HIN consistently and significantly outperforms state-of-the-art alternatives on each of these tasks, on four datasets.
  arXiv  Detail & Related papers  (2020-07-07T03:36:28Z)

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.