VDTuner: Automated Performance Tuning for Vector Data Management Systems

Vector data management systems (VDMSs) have become an indispensable cornerstone in large-scale information retrieval and machine learning systems like large language models. To enhance the efficiency and flexibility of similarity search, VDMS exposes many tunable index parameters and system parameters for users to specify. However, due to the inherent characteristics of VDMS, automatic performance tuning for VDMS faces several critical challenges, which cannot be well addressed by the existing auto-tuning methods. In this paper, we introduce VDTuner, a learning-based automatic performance tuning framework for VDMS, leveraging multi-objective Bayesian optimization. VDTuner overcomes the challenges associated with VDMS by efficiently exploring a complex multi-dimensional parameter space without requiring any prior knowledge. Moreover, it is able to achieve a good balance between search speed and recall rate, delivering an optimal configuration. Extensive evaluations demonstrate that VDTuner can markedly improve VDMS performance (14.12% in search speed and 186.38% in recall rate) compared with default setting, and is more efficient compared with state-of-the-art baselines (up to 3.57 times faster in terms of tuning time). In addition, VDTuner is scalable to specific user preference and cost-aware optimization objective. VDTuner is available online at https://github.com/tiannuo-yang/VDTuner.

pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning

Federated learning (FL) has been widely adopted for collaborative training on decentralized data. However, it faces the challenges of data, system, and model heterogeneity. This has inspired the emergence of model-heterogeneous personalized federated learning (MHPFL). Nevertheless, the problem of ensuring data and model privacy, while achieving good model performance and keeping communication and computation costs low remains open in MHPFL. To address this problem, we propose a model-heterogeneous personalized Federated learning with Mixture of Experts (pFedMoE) method. It assigns a shared homogeneous small feature extractor and a local gating network for each client's local heterogeneous large model. Firstly, during local training, the local heterogeneous model's feature extractor acts as a local expert for personalized feature (representation) extraction, while the shared homogeneous small feature extractor serves as a global expert for generalized feature extraction. The local gating network produces personalized weights for extracted representations from both experts on each data sample. The three models form a local heterogeneous MoE. The weighted mixed representation fuses generalized and personalized features and is processed by the local heterogeneous large model's header with personalized prediction information. The MoE and prediction header are updated simultaneously. Secondly, the trained local homogeneous small feature extractors are sent to the server for cross-client information fusion via aggregation. Overall, pFedMoE enhances local model personalization at a fine-grained data level, while supporting model heterogeneity.

FedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning

Federated learning (FL) is widely employed for collaborative training on decentralized data but faces challenges like data, system, and model heterogeneity. This prompted the emergency of model-heterogeneous personalized federated learning (MHPFL). However, concerns persist regarding data and model privacy, model performance, communication, and computational costs in current MHPFL methods. To tackle these concerns, we propose a novel model-heterogeneous personalized Federated learning algorithm (FedMoE) with the Mixture of Experts (MoE), renowned for enhancing large language models (LLMs). It assigns a shared homogeneous small feature extractor and a local gating network for each client's local heterogeneous large model. (1) During local training, the local heterogeneous model's feature extractor acts as a local expert for personalized feature (representation) extraction, while the shared homogeneous small feature extractor serves as a global expert for generalized feature extraction. The local gating network produces personalized weights for extracted representations from both experts on each data sample. The three models form a local heterogeneous MoE. The weighted mixed representation fuses global generalized and local personalized features and is processed by the local heterogeneous large model's header with personalized prediction information for output. The MoE and prediction header are updated synchronously. (2) The trained local homogeneous small feature extractors are sent to the server for cross-client information fusion via aggregation. Briefly, FedMoE first enhances local model personalization at a fine-grained data level while supporting model heterogeneity.

DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution

Recent research on deep convolutional neural networks (CNNs) has provided a significant performance boost on efficient super-resolution (SR) tasks by trading off the performance and applicability. However, most existing methods focus on subtracting feature processing consumption to reduce the parameters and calculations without refining the immediate features, which leads to inadequate information in the restoration. In this paper, we propose a lightweight network termed DDistill-SR, which significantly improves the SR quality by capturing and reusing more helpful information in a static-dynamic feature distillation manner. Specifically, we propose a plug-in reparameterized dynamic unit (RDU) to promote the performance and inference cost trade-off. During the training phase, the RDU learns to linearly combine multiple reparameterizable blocks by analyzing varied input statistics to enhance layer-level representation. In the inference phase, the RDU is equally converted to simple dynamic convolutions that explicitly capture robust dynamic and static feature maps. Then, the information distillation block is constructed by several RDUs to enforce hierarchical refinement and selective fusion of spatial context information. Furthermore, we propose a dynamic distillation fusion (DDF) module to enable dynamic signals aggregation and communication between hierarchical modules to further improve performance. Empirical results show that our DDistill-SR outperforms the baselines and achieves state-of-the-art results on most super-resolution domains with much fewer parameters and less computational overhead. We have released the code of DDistill-SR at https://github.com/icandle/DDistill-SR.

FedSSA: Semantic Similarity-based Aggregation for Efficient Model-Heterogeneous Personalized Federated Learning

Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (a.k.a. FL clients) to train the same local model. This design is not well-suited for scenarios involving data and/or system heterogeneity. Model-Heterogeneous Personalized FL (MHPFL) has emerged to address this challenge. Existing MHPFL approaches often rely on having a public dataset with the same nature of the learning task, or incur high computation and communication costs. To address these limitations, we propose the Federated Semantic Similarity Aggregation (FedSSA) approach, which splits each client's model into a heterogeneous (structure-different) feature extractor and a homogeneous (structure-same) classification header. It performs local-to-global knowledge transfer via semantic similarity-based header parameter aggregation. In addition, global-to-local knowledge transfer is achieved via an adaptive parameter stabilization strategy which fuses the seen-class parameters of historical local headers with that of the latest global header for each client. In this way, FedSSA does not rely on public datasets, while only requiring partial header parameter transmission (thereby saving costs). Theoretical analysis proves the convergence of FedSSA. Extensive experiments demonstrate that FedSSA achieves up to $3.62 \times\%$ higher accuracy, $15.54$ times higher communication efficiency, and $15.52 \times$ higher computational efficiency compared to 7 state-of-the-art MHPFL baselines.

pFedES: Model Heterogeneous Personalized Federated Learning with Feature Extractor Sharing

As a privacy-preserving collaborative machine learning paradigm, federated learning (FL) has attracted significant interest from academia and the industry alike. To allow each data owner (a.k.a., FL clients) to train a heterogeneous and personalized local model based on its local data distribution, system resources and requirements on model structure, the field of model-heterogeneous personalized federated learning (MHPFL) has emerged. Existing MHPFL approaches either rely on the availability of a public dataset with special characteristics to facilitate knowledge transfer, incur high computation and communication costs, or face potential model leakage risks. To address these limitations, we propose a model-heterogeneous personalized Federated learning approach based on feature Extractor Sharing (pFedES). It incorporates a small homogeneous feature extractor into each client's heterogeneous local model. Clients train them via the proposed iterative learning method to enable the exchange of global generalized knowledge and local personalized knowledge. The small local homogeneous extractors produced after local training are uploaded to the FL server and for aggregation to facilitate easy knowledge sharing among clients. We theoretically prove that pFedES can converge over wall-to-wall time. Extensive experiments on two real-world datasets against six state-of-the-art methods demonstrate that pFedES builds the most accurate model, while incurring low communication and computation costs. Compared with the best-performing baseline, it achieves 1.61% higher test accuracy, while reducing communication and computation costs by 99.6% and 82.9%, respectively.

FedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning

Federated learning (FL) is an emerging machine learning paradigm in which a central server coordinates multiple participants (a.k.a. FL clients) to train a model collaboratively on decentralized data with privacy protection. This paradigm constrains that all clients have to train models with the same structures (homogeneous). In practice, FL often faces statistical heterogeneity, system heterogeneity and model heterogeneity challenges. These challenging issues inspire the field of Model-Heterogeneous Personalized Federated Learning (MHPFL) which aims to train a personalized and heterogeneous local model for each FL client. Existing MHPFL approaches cannot achieve satisfactory model performance, acceptable computational overhead and efficient communication simultaneously. To bridge this gap, we propose a novel computation- and communication-efficient model-heterogeneous personalized Federated learning framework based on LoRA tuning (FedLoRA). It is designed to incorporate a homogeneous small adapter for each client's heterogeneous local model. Both models are trained following the proposed iterative training for global-local knowledge exchange. The homogeneous small local adapters are sent to the FL server to be aggregated into a global adapter. In this way, FL clients can train heterogeneous local models without incurring high computation and communication costs. We theoretically prove the non-convex convergence rate of FedLoRA. Extensive experiments on two real-world datasets demonstrate that FedLoRA outperforms six state-of-the-art baselines, beating the best approach by 1.35% in terms of test accuracy, 11.81 times computation overhead reduction and 7.41 times communication cost saving.

FedGH: Heterogeneous Federated Learning with Generalized Global Header

Federated learning (FL) is an emerging machine learning paradigm that allows multiple parties to train a shared model collaboratively in a privacy-preserving manner. Existing horizontal FL methods generally assume that the FL server and clients hold the same model structure. However, due to system heterogeneity and the need for personalization, enabling clients to hold models with diverse structures has become an important direction. Existing model-heterogeneous FL approaches often require publicly available datasets and incur high communication and/or computational costs, which limit their performances. To address these limitations, we propose the Federated Global prediction Header (FedGH) approach. It is a communication and computation-efficient model-heterogeneous FL framework which trains a shared generalized global prediction header with representations extracted by heterogeneous extractors for clients' models at the FL server. The trained generalized global prediction header learns from different clients. The acquired global knowledge is then transferred to clients to substitute each client's local prediction header. We derive the non-convex convergence rate of FedGH. Extensive experiments on two real-world datasets demonstrate that FedGH achieves significantly more advantageous performance in both model-homogeneous and -heterogeneous FL scenarios compared to seven state-of-the-art personalized FL models, beating the best-performing baseline by up to 8.87% (for model-homogeneous FL) and 1.83% (for model-heterogeneous FL) in terms of average test accuracy, while saving up to 85.53% of communication overhead.

Multi-scale Attention Network for Single Image Super-Resolution

By exploiting large kernel decomposition and attention mechanisms, convolutional neural networks (CNN) can compete with transformer-based methods in many high-level computer vision tasks. However, due to the advantage of long-range modeling, the transformers with self-attention still dominate the low-level vision, including the super-resolution task. In this paper, we propose a CNN-based multi-scale attention network (MAN), which consists of multi-scale large kernel attention (MLKA) and a gated spatial attention unit (GSAU), to improve the performance of convolutional SR networks. Within our MLKA, we rectify LKA with multi-scale and gate schemes to obtain the abundant attention map at various granularity levels, therefore jointly aggregating global and local information and avoiding the potential blocking artifacts. In GSAU, we integrate gate mechanism and spatial attention to remove the unnecessary linear layer and aggregate informative spatial context. To confirm the effectiveness of our designs, we evaluate MAN with multiple complexities by simply stacking different numbers of MLKA and GSAU. Experimental results illustrate that our MAN can achieve varied trade-offs between state-of-the-art performance and computations. Code is available at https://github.com/icandle/MAN.