Federated Learning is an emerging direction in distributed machine learning that en-ables jointly training a model without sharing the data. Since the data is distributed across many edge devices through wireless / long-distance connections, federated learning suffers from inevitable high communication latency. However, the latency issues are undermined in the current literature [15] and existing approaches suchas FedAvg [27] become less efficient when the latency increases. To over comethe problem, we propose \textbf{D}elayed \textbf{G}radient \textbf{A}veraging (DGA), which delays the averaging step to improve efficiency and allows local computation in parallel tocommunication. We theoretically prove that DGA attains a similar convergence rate as FedAvg, and empirically show that our algorithm can tolerate high network latency without compromising accuracy. Specifically, we benchmark the training speed on various vision (CIFAR, ImageNet) and language tasks (Shakespeare),with both IID and non-IID partitions, and show DGA can bring 2.55$\times$ to 4.07$\times$ speedup. Moreover, we built a 16-node Raspberry Pi cluster and show that DGA can consistently speed up real-world federated learning applications.

Abstract: The sophistication of modern malware, specifically regarding communication with Command and Control (C2) servers, has rendered static blacklist - based defenses obsolete. The use of Domain Generation Algorithms (DGA) allows attackers to generate thousands of dynamic addresses daily, hindering blocking by traditional firewalls. This paper aims to propose and evaluate a method for detecting DGA domains using Deep Learning and Natural Language Processing (NLP) techniques. The methodology consisted of collecting a hybrid database containing 50,000 legitimate and 50,000 malicious domains, followed by the extraction of lexical features and the training of a Recurrent Neural Network (LSTM). Results demonstrated that while statistical entropy analysis is effective for simple DGAs, the Neural Network approach presents superiority in detecting complex patterns, reaching 97.2% accuracy and reducing the false positive rate in ambiguous lawful traffic scenarios.

Large language models (LLMs) are commonly trained on multi-domain datasets, where domain sampling strategies significantly impact model performance due to varying domain importance across downstream tasks. Existing approaches for optimizing domain-level sampling strategies struggle with maintaining intra-domain consistency and accurately measuring domain impact. In this paper, we present Domain Impact-aware Data Sampling (DIDS). To ensure intra-domain consistency, a gradient clustering algorithm is proposed to group training data based on their learning effects, where a proxy language model and dimensionality reduction are employed to reduce computational overhead. To accurately measure domain impact, we develop a Fisher Information Matrix (FIM) guided metric that quantifies how domain-specific parameter updates affect the model's output distributions on downstream tasks, with theoretical guarantees. Furthermore, to determine optimal sampling ratios, DIDS combines both the FIM-guided domain impact assessment and loss learning trajectories that indicate domain-specific potential, while accounting for diminishing marginal returns. Extensive experiments demonstrate that DIDS achieves 3.4% higher average performance while maintaining comparable training efficiency. The code is available at https://github.com/shiweijiezero/DIDS.

Federated Learning is an emerging direction in distributed machine learning that enables jointly training a model without sharing the data.

The results confirm that the post-processing helps to improve the resolution of the attribution. We provide the simple implementation of our algorithm in Python language. We provide the ablation study on (1) the usage of ReLU and (2) WC/EPC masks in this section. To achieve better performance in both metrics, we suggest to use both masks. We provide the quantitative evaluation on different attribution methods.

Federated Learning is an emerging direction in distributed machine learning that en-ables jointly training a model without sharing the data. Since the data is distributed across many edge devices through wireless / long-distance connections, federated learning suffers from inevitable high communication latency. However, the latency issues are undermined in the current literature [15] and existing approaches suchas FedAvg [27] become less efficient when the latency increases. To over comethe problem, we propose \textbf{D}elayed \textbf{G}radient \textbf{A}veraging (DGA), which delays the averaging step to improve efficiency and allows local computation in parallel tocommunication. We theoretically prove that DGA attains a similar convergence rate as FedAvg, and empirically show that our algorithm can tolerate high network latency without compromising accuracy. Specifically, we benchmark the training speed on various vision (CIFAR, ImageNet) and language tasks (Shakespeare),with both IID and non-IID partitions, and show DGA can bring 2.55 \times to 4.07 \times speedup.

The composition of training data mixtures is critical for effectively training large language models (LLMs), as it directly impacts their performance on downstream tasks. Our goal is to identify an optimal data mixture to specialize an LLM for a specific task with access to only a few examples. Traditional approaches to this problem include ad-hoc reweighting methods, importance sampling, and gradient alignment techniques. This paper focuses on gradient alignment and introduces Dynamic Gradient Alignment (DGA), a scalable online gradient alignment algorithm. DGA dynamically estimates the pre-training data mixture on which the models' gradients align as well as possible with those of the model on the specific task. DGA is the first gradient alignment approach that incurs minimal overhead compared to standard pre-training and outputs a competitive model, eliminating the need for retraining the model. Experimentally, we demonstrate significant improvements over importance sampling in two key scenarios: (i) when the pre-training set is small and importance sampling overfits due to limited data; and (ii) when there is insufficient specialized data, trapping importance sampling on narrow pockets of data. Our findings underscore the effectiveness of gradient alignment methods in optimizing training data mixtures, particularly in data-constrained environments, and offer a practical solution for enhancing LLM performance on specific tasks with limited data availability.

I've been in the entertainment industry since I was nine. I joined the Screen Actors Guild (SAG) when I was 11 in 1977, the Writers Guild of America (WGA) when I was 22, and the Directors Guild of America (DGA) the following year. I got my start as a child actor on Broadway, studied film at NYU, then went on to act in movies like The Lost Boys and the Bill & Ted franchise while writing and directing my own narrative work. I've lived through several labor crises and strikes, but none like our current work shutdown, which began last spring when all three unions' contracts were simultaneously due for renegotiation and the Alliance of Motion Picture and Television Producers (AMPTP) refused their terms. The unifying stress point for labor is the devaluing of the worker, which reached a boiling point with the rapid advancement of highly sophisticated and ubiquitous machine learning tools. Actors have been replaced by AI replications of their likenesses, or their voices have been stolen outright.