arXiv subjects

Fang Wei

Publications and source records attributed to Fang Wei.

4 recordsLinked to original sources

arXiv2026

EvoCSFL: Surrogate-Assisted Evolutionary Client Selection for Efficient and Robust Federated Learning

The heterogeneity of client data and systems makes it difficult to achieve satisfactory convergence speed and robustness in federated learning with random client selection. To address this issue, this paper proposes a surrogate-assisted client evolutionary selection framework for federated learning. In this framework, some typical client selection strategies are first used to generate candidate sets, and a metric function that integrates model performance, communication latency, and energy consumption is developed to formulate the client selection problem as a combinatorial optimization one. Subsequently, a surrogate model is constructed using the candidate selections and metric to efficiently approximate the performance of selected client subsets. An evolutionary algorithm is employed to search the combinatorial space of client selections, guided by the surrogate model to accelerate convergence. Experiments on MNIST, CIFAR10, CINIC10, and TinyImageNet demonstrate that the proposed algorithm achieves faster convergence, lower energy consumption, and improved robustness compared to existing methods.

cs.LG↗

arXiv2026

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a context length of one million tokens. DeepSeek-V4 series incorporate several key upgrades in architecture and optimization: (1) a hybrid attention architecture that combines Compressed Sparse Attention (CSA) and Heavily Compressed Attention (HCA) to improve long-context efficiency; (2) Manifold-Constrained Hyper-Connections (mHC) that enhance conventional residual connections; (3) and the Muon optimizer for faster convergence and greater training stability. We pre-train both models on more than 32T diverse and high-quality tokens, followed by a comprehensive post-training pipeline that unlocks and further enhances their capabilities. DeepSeek-V4-Pro-Max, the maximum reasoning effort mode of DeepSeek-V4-Pro, redefines the state-of-the-art for open models, outperforming its predecessors in core tasks. Meanwhile, DeepSeek-V4 series are highly efficient in long-context scenarios. In the one-million-token context setting, DeepSeek-V4-Pro requires only 27% of single-token inference FLOPs and 10% of KV cache compared with DeepSeek-V3.2. This enables us to routinely support one-million-token contexts, thereby making long-horizon tasks and further test-time scaling more feasible. The model checkpoints are available at https://huggingface.co/collections/deepseek-ai/deepseek-v4.

cs.CL↗

arXiv2022

Machine Learning Prediction of COVID-19 Severity Levels From Salivaomics Data

The clinical spectrum of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the strain of coronavirus that caused the COVID-19 pandemic, is broad, extending from asymptomatic infection to severe immunopulmonary reactions that, if not categorized properly, may be life-threatening. Researchers rate COVID-19 patients on a scale from 1 to 8 according to the severity level of COVID-19, 1 being healthy and 8 being extremely sick, based on a multitude of factors including number of clinic visits, days since the first sign of symptoms, and more. However, there are two issues with the current state of severity level designation. Firstly, there exists variation among researchers in determining these patient scores, which may lead to improper treatment. Secondly, researchers use a variety of metrics to determine patient severity level, including metrics involving plasma collection that require invasive procedures. This project aims to remedy both issues by introducing a machine learning framework that unifies severity level designations based on noninvasive saliva biomarkers. Our results show that we can successfully use machine learning on salivaomics data to predict the severity level of COVID-19 patients, indicating the presence of viral load using saliva biomarkers.

q-bio.QM↗

arXiv2008

Monadic Datalog over Finite Structures with Bounded Treewidth

Bounded treewidth and Monadic Second Order (MSO) logic have proved to be key concepts in establishing fixed-parameter tractability results. Indeed, by Courcelle's Theorem we know: Any property of finite structures, which is expressible by an MSO sentence, can be decided in linear time (data complexity) if the structures have bounded treewidth. In principle, Courcelle's Theorem can be applied directly to construct concrete algorithms by transforming the MSO evaluation problem into a tree language recognition problem. The latter can then be solved via a finite tree automaton (FTA). However, this approach has turned out to be problematical, since even relatively simple MSO formulae may lead to a ``state explosion'' of the FTA. In this work we propose monadic datalog (i.e., datalog where all intentional predicate symbols are unary) as an alternative method to tackle this class of fixed-parameter tractable problems. We show that if some property of finite structures is expressible in MSO then this property can also be expressed by means of a monadic datalog program over the structure plus the tree decomposition. Moreover, we show that the resulting fragment of datalog can be evaluated in linear time (both w.r.t. the program size and w.r.t. the data size). This new approach is put to work by devising new algorithms for the 3-Colorability problem of graphs and for the PRIMALITY problem of relational schemas (i.e., testing if some attribute in a relational schema is part of a key). We also report on experimental results with a prototype implementation.

cs.DB↗