Related papers: Federated-inspired Single-cell Batch Integration i…
Single-cell RNA-seq foundation models achieve strong performance on downstream tasks but remain black boxes, limiting their utility for biological discovery. Recent work has shown that sparse dictionary learning can extract concepts from…
State-of-the-art federated learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. For neural networks, even when centralized SGD easily finds a solution that is…
Fine-tuning pre-trained models is a popular approach in machine learning for solving complex tasks with moderate data. However, fine-tuning the entire pre-trained model is ineffective in federated data scenarios where local data…
Federated learning allows a large number of devices to jointly learn a model without sharing data. In this work, we enable clients with limited computing power to perform action recognition, a computationally heavy task. We first perform…
Federated learning (FL) has emerged as a widely adopted training paradigm for privacy-preserving machine learning. While the SGD-based FL algorithms have demonstrated considerable success in the past, there is a growing trend towards…
The increasing adoption of large language models (LLMs) necessitates inference serving systems that can deliver both high throughput and low latency. Deploying LLMs with hundreds of billions of parameters on memory-constrained GPUs exposes…
A central goal in systems biology and drug discovery is to predict the transcriptional response of cells to perturbations. This task is challenging due to the noisy and sparse nature of single-cell measurements, as well as the fact that…
Single-cell RNA-sequencing (scRNA-seq) has become a routinely used technique to quantify the gene expression profile of thousands of single cells simultaneously. Analysis of scRNA-seq data plays an important role in the study of cell states…
Large language models (LLMs) have demonstrated remarkable advancements, primarily due to their capabilities in modeling the hidden relationships within text sequences. This innovation presents a unique opportunity in the field of life…
Predicting drug-induced cellular state changes at single-cell resolution remains a central challenge in virtual cell modeling, particularly under out-of-distribution (OOD) conditions. Current approaches predominantly rely on RNA-based…
This work presents a new method for enhancing communication efficiency in stochastic Federated Learning that trains over-parameterized random networks. In this setting, a binary mask is optimized instead of the model weights, which are kept…
While single-cell RNA sequencing provides an understanding of the transcriptome of individual cells, its high sparsity, often termed dropout, hampers the capture of significant cell-cell relationships. Here, we propose scFP (single-cell…
Reasoning is a key component of language understanding in Large Language Models. While Chain-of-Thought prompting enhances performance via explicit intermediate steps, it suffers from sufficient token overhead and a fixed reasoning…
Neural networks often struggle with catastrophic forgetting when learning sequences of tasks or data streams, unlike humans who can continuously learn and consolidate new concepts even in the absence of explicit cues. Online…
As an emerging paradigm of federated learning, asynchronous federated learning offers significant speed advantages over traditional synchronous federated learning. Unlike synchronous federated learning, which requires waiting for all…
Synthetic data augmentation has emerged as a promising solution when pre-training is constrained by data rather than compute. We study how to design synthetic data algorithms that achieve better loss scaling: not only lowering loss at…
Healthcare fraud detection remains a critical challenge due to limited availability of labeled data, constantly evolving fraud tactics, and the high dimensionality of medical records. Traditional supervised methods are challenged by extreme…
Federated learning enables training machine learning models while preserving the privacy of participants. Surprisingly, there is no differentially private distributed method for smooth, non-convex optimization problems. The reason is that…
In deep learning, mini-batch training is commonly used to optimize network parameters. However, the traditional mini-batch method may not learn the under-represented samples and complex patterns in the data, leading to a longer time for…
Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…