A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models

Due to the continuous emergence of new data, version updates have become an indispensable requirement for Large Language Models (LLMs). The training paradigms for version updates of LLMs include pre-training from scratch (PTFS) and continual pre-training (CPT). Preliminary experiments demonstrate that PTFS achieves better pre-training performance, while CPT has lower training cost. Moreover, their performance and training cost gaps widen progressively with version updates. To investigate the underlying reasons for this phenomenon, we analyze the effect of learning rate adjustments during the two stages of CPT: preparing an initialization checkpoint and continual pre-training based on this checkpoint. We find that a large learning rate in the first stage and a complete learning rate decay process in the second stage are crucial for version updates of LLMs. Hence, we propose a learning rate path switching training paradigm. Our paradigm comprises one main path, where we pre-train a LLM with the maximal learning rate, and multiple branching paths, each of which corresponds to an update of the LLM with newly-added training data. Extensive experiments demonstrate the effectiveness and generalization of our paradigm. Particularly, when training four versions of LLMs, our paradigm reduces the total training cost to 58% compared to PTFS, while maintaining comparable pre-training performance.

Reducing Semantic Ambiguity In Domain Adaptive Semantic Segmentation Via Probabilistic Prototypical Pixel Contrast

Domain adaptation aims to reduce the model degradation on the target domain caused by the domain shift between the source and target domains. Although encouraging performance has been achieved by combining cognitive learning with the self-training paradigm, they suffer from ambiguous scenarios caused by scale, illumination, or overlapping when deploying deterministic embedding. To address these issues, we propose probabilistic proto-typical pixel contrast (PPPC), a universal adaptation framework that models each pixel embedding as a probability via multivariate Gaussian distribution to fully exploit the uncertainty within them, eventually improving the representation quality of the model. In addition, we derive prototypes from probability estimation posterior probability estimation which helps to push the decision boundary away from the ambiguity points. Moreover, we employ an efficient method to compute similarity between distributions, eliminating the need for sampling and reparameterization, thereby significantly reducing computational overhead. Further, we dynamically select the ambiguous crops at the image level to enlarge the number of boundary points involved in contrastive learning, which benefits the establishment of precise distributions for each category. Extensive experimentation demonstrates that PPPC not only helps to address ambiguity at the pixel level, yielding discriminative representations but also achieves significant improvements in both synthetic-to-real and day-to-night adaptation tasks. It surpasses the previous state-of-the-art (SOTA) by +5.2% mIoU in the most challenging daytime-to-nighttime adaptation scenario, exhibiting stronger generalization on other unseen datasets. The code and models are available at https://github.com/DarlingInTheSV/Probabilistic-Prototypical-Pixel-Contrast.

Strawberry detection and counting based on YOLOv7 pruning and information based tracking algorithm

The strawberry industry yields significant economic benefits for Florida, yet the process of monitoring strawberry growth and yield is labor-intensive and costly. The development of machine learning-based detection and tracking methodologies has been used for helping automated monitoring and prediction of strawberry yield, still, enhancement has been limited as previous studies only applied the deep learning method for flower and fruit detection, which did not consider the unique characteristics of image datasets collected by the machine vision system. This study proposed an optimal pruning of detection heads of the deep learning model (YOLOv7 and its variants) that could achieve fast and precise strawberry flower, immature fruit, and mature fruit detection. Thereafter, an enhanced object tracking algorithm, which is called the Information Based Tracking Algorithm (IBTA) utilized the best detection result, removed the Kalman Filter, and integrated moving direction, velocity, and spatial information to improve the precision in strawberry flower and fruit tracking. The proposed pruning of detection heads across YOLOv7 variants, notably Pruning-YOLOv7-tiny with detection head 3 and Pruning-YOLOv7-tiny with heads 2 and 3 achieved the best inference speed (163.9 frames per second) and detection accuracy (89.1%), respectively. On the other hand, the effect of IBTA was proved by comparing it with the centroid tracking algorithm (CTA), the Multiple Object Tracking Accuracy (MOTA) and Multiple Object Tracking Precision (MOTP) of IBTA were 12.3% and 6.0% higher than that of CTA, accordingly. In addition, other object-tracking evaluation metrics, including IDF1, IDR, IDP, MT, and IDs, show that IBTA performed better than CTA in strawberry flower and fruit tracking.

Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval

To achieve non-parametric NMT domain adaptation, $k$-Nearest-Neighbor Machine Translation ($k$NN-MT) constructs an external datastore to store domain-specific translation knowledge, which derives a $k$NN distribution to interpolate the prediction distribution of the NMT model via a linear interpolation coefficient $\lambda$. Despite its success, $k$NN retrieval at each timestep leads to substantial time overhead. To address this issue, dominant studies resort to $k$NN-MT with adaptive retrieval ($k$NN-MT-AR), which dynamically estimates $\lambda$ and skips $k$NN retrieval if $\lambda$ is less than a fixed threshold. Unfortunately, $k$NN-MT-AR does not yield satisfactory results. In this paper, we first conduct a preliminary study to reveal two key limitations of $k$NN-MT-AR: 1) the optimization gap leads to inaccurate estimation of $\lambda$ for determining $k$NN retrieval skipping, and 2) using a fixed threshold fails to accommodate the dynamic demands for $k$NN retrieval at different timesteps. To mitigate these limitations, we then propose $k$NN-MT with dynamic retrieval ($k$NN-MT-DR) that significantly extends vanilla $k$NN-MT in two aspects. Firstly, we equip $k$NN-MT with a MLP-based classifier for determining whether to skip $k$NN retrieval at each timestep. Particularly, we explore several carefully-designed scalar features to fully exert the potential of the classifier. Secondly, we propose a timestep-aware threshold adjustment method to dynamically generate the threshold, which further improves the efficiency of our model. Experimental results on the widely-used datasets demonstrate the effectiveness and generality of our model.\footnote{Our code is available at \url{https://github.com/DeepLearnXMU/knn-mt-dr}.

VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data

In the blind single image super-resolution (SISR) task, existing works have been successful in restoring image-level unknown degradations. However, when a single video frame becomes the input, these works usually fail to address degradations caused by video compression, such as mosquito noise, ringing, blockiness, and staircase noise. In this work, we for the first time, present a video compression-based degradation model to synthesize low-resolution image data in the blind SISR task. Our proposed image synthesizing method is widely applicable to existing image datasets, so that a single degraded image can contain distortions caused by the lossy video compression algorithms. This overcomes the leak of feature diversity in video data and thus retains the training efficiency. By introducing video coding artifacts to SISR degradation models, neural networks can super-resolve images with the ability to restore video compression degradations, and achieve better results on restoring generic distortions caused by image compression as well. Our proposed approach achieves superior performance in SOTA no-reference Image Quality Assessment, and shows better visual quality on various datasets. In addition, we evaluate the SISR neural network trained with our degradation model on video super-resolution (VSR) datasets. Compared to architectures specifically designed for the VSR purpose, our method exhibits similar or better performance, evidencing that the presented strategy on infusing video-based degradation is generalizable to address more complicated compression artifacts even without temporal cues.

Personalized Federated Learning via Amortized Bayesian Meta-Learning

Federated learning is a decentralized and privacy-preserving technique that enables multiple clients to collaborate with a server to learn a global model without exposing their private data. However, the presence of statistical heterogeneity among clients poses a challenge, as the global model may struggle to perform well on each client's specific task. To address this issue, we introduce a new perspective on personalized federated learning through Amortized Bayesian Meta-Learning. Specifically, we propose a novel algorithm called \emph{FedABML}, which employs hierarchical variational inference across clients. The global prior aims to capture representations of common intrinsic structures from heterogeneous clients, which can then be transferred to their respective tasks and aid in the generation of accurate client-specific approximate posteriors through a few local updates. Our theoretical analysis provides an upper bound on the average generalization error and guarantees the generalization performance on unseen data. Finally, several empirical results are implemented to demonstrate that \emph{FedABML} outperforms several competitive baselines.

Robust Graph Structure Learning with the Alignment of Features and Adjacency Matrix

To improve the robustness of graph neural networks (GNN), graph structure learning (GSL) has attracted great interest due to the pervasiveness of noise in graph data. Many approaches have been proposed for GSL to jointly learn a clean graph structure and corresponding representations. To extend the previous work, this paper proposes a novel regularized GSL approach, particularly with an alignment of feature information and graph information, which is motivated mainly by our derived lower bound of node-level Rademacher complexity for GNNs. Additionally, our proposed approach incorporates sparse dimensional reduction to leverage low-dimensional node features that are relevant to the graph structure. To evaluate the effectiveness of our approach, we conduct experiments on real-world graphs. The results demonstrate that our proposed GSL method outperforms several competitive baselines, especially in scenarios where the graph structures are heavily affected by noise. Overall, our research highlights the importance of integrating feature and graph information alignment in GSL, as inspired by our derived theoretical result, and showcases the superiority of our approach in handling noisy graph structures through comprehensive experiments on real-world datasets.

Stability and Generalization of $\ell_p$-Regularized Stochastic Learning for GCN

Graph convolutional networks (GCN) are viewed as one of the most popular representations among the variants of graph neural networks over graph data and have shown powerful performance in empirical experiments. That $\ell_2$-based graph smoothing enforces the global smoothness of GCN, while (soft) $\ell_1$-based sparse graph learning tends to promote signal sparsity to trade for discontinuity. This paper aims to quantify the trade-off of GCN between smoothness and sparsity, with the help of a general $\ell_p$-regularized $(1<p\leq 2)$ stochastic learning proposed within. While stability-based generalization analyses have been given in prior work for a second derivative objectiveness function, our $\ell_p$-regularized learning scheme does not satisfy such a smooth condition. To tackle this issue, we propose a novel SGD proximal algorithm for GCNs with an inexact operator. For a single-layer GCN, we establish an explicit theoretical understanding of GCN with the $\ell_p$-regularized stochastic learning by analyzing the stability of our SGD proximal algorithm. We conduct multiple empirical experiments to validate our theoretical findings.

MMVC: Learned Multi-Mode Video Compression with Block-based Prediction Mode Selection and Density-Adaptive Entropy Coding

Learning-based video compression has been extensively studied over the past years, but it still has limitations in adapting to various motion patterns and entropy models. In this paper, we propose multi-mode video compression (MMVC), a block wise mode ensemble deep video compression framework that selects the optimal mode for feature domain prediction adapting to different motion patterns. Proposed multi-modes include ConvLSTM-based feature domain prediction, optical flow conditioned feature domain prediction, and feature propagation to address a wide range of cases from static scenes without apparent motions to dynamic scenes with a moving camera. We partition the feature space into blocks for temporal prediction in spatial block-based representations. For entropy coding, we consider both dense and sparse post-quantization residual blocks, and apply optional run-length coding to sparse residuals to improve the compression rate. In this sense, our method uses a dual-mode entropy coding scheme guided by a binary density map, which offers significant rate reduction surpassing the extra cost of transmitting the binary selection map. We validate our scheme with some of the most popular benchmarking datasets. Compared with state-of-the-art video compression schemes and standard codecs, our method yields better or competitive results measured with PSNR and MS-SSIM.

Stochastic Clustered Federated Learning

Federated learning is a distributed learning framework that takes full advantage of private data samples kept on edge devices. In real-world federated learning systems, these data samples are often decentralized and Non-Independently Identically Distributed (Non-IID), causing divergence and performance degradation in the federated learning process. As a new solution, clustered federated learning groups federated clients with similar data distributions to impair the Non-IID effects and train a better model for every cluster. This paper proposes StoCFL, a novel clustered federated learning approach for generic Non-IID issues. In detail, StoCFL implements a flexible CFL framework that supports an arbitrary proportion of client participation and newly joined clients for a varying FL system, while maintaining a great improvement in model performance. The intensive experiments are conducted by using four basic Non-IID settings and a real-world dataset. The results show that StoCFL could obtain promising cluster results even when the number of clusters is unknown. Based on the client clustering results, models trained with StoCFL outperform baseline approaches in a variety of contexts.