← Back to all news
arXiv Machine Learning By Iason Ofeidis, Leandros Tassiulas

Contribution-Aware Bandwidth Allocation for Multimodal Split Learning

Read the original on arXiv Machine Learning →

The paper introduces ModalShare, a bandwidth allocation method for multimodal split learning that assigns each modality a keep‑ratio based on its Shapley contribution score. Unlike existing compression schemes that split the uplink budget proportionally to activation size, ModalShare explicitly optimizes the split across modalities, requiring no extra uplink traffic or client computation. Experiments on CREMA‑D and MVSA datasets show that ModalShare improves accuracy by 12.4–15.4 percentage points over equal keep‑ratios under a 5× compression budget, outperforming three compressors across multiple datasets and budgets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 11

EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression

The paper introduces EMMI, a framework that enables communication‑efficient inference of multimodal large language models (MLLMs) on edge devices. EMMI encodes each sensor modality separately, fuses the representations, and compresses them into a compact latent vector that is transmitted to a server for high‑capacity reasoning. Experiments on a multimodal benchmark show that EMMI can cut the communication payload by 32× while keeping accuracy comparable, achieving up to a 3.4× reduction in end‑to‑end inference latency under bandwidth‑constrained conditions.

By Motahare Mounesan, Irfan Khan
efficiencymultimodalbenchmarkssafety
More like this →
arXiv Machine Learning
Sep 10

Dense Structural Compression of Transformers via Gauge-Correct Channel Removal

The paper introduces GaugeLasso, a method that applies symmetric group‑lasso penalties to transformer channels during training, enabling entire tensor slices to be zeroed out while maintaining dense tensors for GPU efficiency. By calibrating channel penalties based on inference utility per compute, the network self‑organizes into depth‑dependent structural profiles that can be dramatically smaller than the original architecture, achieving up to 255‑fold compression on a polynomial division task and outperforming hand‑designed baselines on language modeling and autoencoding benchmarks. The approach also accelerates training and reveals over‑provisioned axes that guide subsequent design iterations.

By Jed A. Duersch, Na\"im Es-Sebbani, Nathana\"el Haas, Zied Bouraoui
llmsefficiency
More like this →