Zeyu Cao

Zeyu Cao, Wen Yao, Wei Peng et al.

The rapid analysis of thermal stress and deformation plays a pivotal role in the thermal control measures and optimization of the structural design of satellites. For achieving real-time thermal stress and thermal deformation analysis of satellite motherboards, this paper proposes a novel Multi-Task Attention UNet (MTA-UNet) neural network which combines the advantages of both Multi-Task Learning (MTL) and U-Net with attention mechanism. Besides, a physics-informed strategy is used in the training process, where partial differential equations (PDEs) are integrated into the loss functions as residual terms. Finally, an uncertainty-based loss balancing approach is applied to weight different loss functions of multiple training tasks. Experimental results show that the proposed MTA-UNet effectively improves the prediction accuracy of multiple physics tasks compared with Single-Task Learning (STL) models. In addition, the physics-informed method brings less error in the prediction of each task, especially on small data sets. The code can be downloaded at: \url{https://github.com/KomorebiTso/MTA-UNet}.

Zeyu Cao, Yuchi Ma, Zhou Zhang

In the U.S., corn is the most produced crop and has been an essential part of the American diet. To meet the demand for supply chain management and regional food security, accurate and timely large-scale corn yield prediction is attracting more attention in precision agriculture. Recently, remote sensing technology and machine learning methods have been widely explored for crop yield prediction. Currently, most county-level yield prediction models use county-level mean variables for prediction, ignoring much detailed information. Moreover, inconsistent spatial resolution between crop area and satellite sensors results in mixed pixels, which may decrease the prediction accuracy. Only a few works have addressed the mixed pixels problem in large-scale crop yield prediction. To address the information loss and mixed pixels problem, we developed a variational autoencoder (VAE) based multiple instance regression (MIR) model for large-scaled corn yield prediction. We use all unlabeled data to train a VAE and the well-trained VAE for anomaly detection. As a preprocess method, anomaly detection can help MIR find a better representation of every bag than traditional MIR methods, thus better performing in large-scale corn yield prediction. Our experiments showed that variational autoencoder based multiple instance regression (VAEMIR) outperformed all baseline methods in large-scale corn yield prediction. Though a suitable meta parameter is required, VAEMIR shows excellent potential in feature learning and extraction for large-scale corn yield prediction.

Anyu Zhang, Haotian Wu, Zeyu Cao

This paper presents a self-supervised feature learning method for hyperspectral image classification. Our method tries to construct two different views of the raw hyperspectral image through a cross-representation learning method. And then to learn semantically consistent representation over the created views by contrastive learning method. Specifically, four cross-channel-prediction based augmentation methods are naturally designed to utilize the high dimension characteristic of hyperspectral data for the view construction. And the better representative features are learned by maximizing mutual information and minimizing conditional entropy across different views from our contrastive network. This 'Cross-View-Predicton' style is straightforward and gets the state-of-the-art performance of unsupervised classification with a simple SVM classifier.

Lorenzo Sani, Alex Iacob, Zeyu Cao et al.

Generative pre-trained large language models (LLMs) have demonstrated impressive performance over a wide range of tasks, thanks to the unprecedented amount of data they have been trained on. As established scaling laws indicate, LLMs' future performance improvement depends on the amount of computing and data sources they can leverage for pre-training. Federated learning (FL) has the potential to unleash the majority of the planet's data and computational resources, which are underutilized by the data-center-focused training methodology of current LLM practice. Our work presents a robust, flexible, reproducible FL approach that enables large-scale collaboration across institutions to train LLMs. We propose a scalable deployment system called Photon to enable the investigation and development of this new training paradigm for LLM pre-training. We show that Photon can be used by organizations interested in collaborating with their private data sources and computational resources for pre-training LLMs with billions of parameters. This paradigm would mobilize more computational and data resources while matching or potentially exceeding centralized performance. We further show the effectiveness of the federated training scales with model size and present our approach for training billion-scale federated LLMs using limited resources. Thus far, we have used Photon to train LLM models to the size of 7B parameters and anticipate larger models being completed in the near future. Finally, we show that LLM training is highly resilient to the classical challenges of federated statistical and hardware heterogeneity. Furthermore, we show that convergence is robust to partial participation, opening the avenue for compute-efficient collaborative training. Photon will help data-rich actors to become the protagonists of LLMs pre-training instead of leaving the stage to compute-rich actors alone.

Lorenzo Sani, Alex Iacob, Zeyu Cao et al.

Scaling large language models (LLMs) demands extensive data and computing resources, which are traditionally constrained to data centers by the high-bandwidth requirements of distributed training. Low-bandwidth methods like federated learning (FL) could enable collaborative training of larger models across weakly-connected GPUs if they can effectively be used for pre-training. To achieve this, we introduce Photon, the first complete system for federated end-to-end LLM training, leveraging cross-silo FL for global-scale training with minimal communication overheads. Using Photon, we train the first federated family of decoder-only LLMs from scratch. We show that: (1) Photon can train model sizes up to 7B in a federated fashion while reaching an even better perplexity than centralized pre-training; (2) Photon model training time decreases with available compute, achieving a similar compute-time trade-off to centralized; and (3) Photon outperforms the wall-time of baseline distributed training methods by 35% via communicating 64x-512xless. Our proposal is robust to data heterogeneity and converges twice as fast as previous methods like DiLoCo. This surprising data efficiency stems from a unique approach combining small client batch sizes with extremely high learning rates, enabled by federated averaging's robustness to hyperparameters. Photon thus represents the first economical system for global internet-wide LLM pre-training.

Zeyu Cao, Xiaorun Li, Liaoying Zhao

Unsupervised learning methods for feature extraction are becoming more and more popular. We combine the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to design an unsupervised feature learning network for hyperspectral classification. Experiments have proved that our two proposed autoencoder networks have good feature learning capabilities by themselves, and the contrastive learning network we designed can better combine the features of the two to learn more representative features. As a result, our method surpasses other comparison methods in the hyperspectral classification experiments, including some supervised methods. Moreover, our method maintains a fast feature extraction speed than baseline methods. In addition, our method reduces the requirements for huge computing resources, separates feature extraction and contrastive learning, and allows more researchers to conduct research and experiments on unsupervised contrastive learning.