ADMN: A Layer-Wise Adaptive Multimodal Network for Dynamic Input Noise and Compute Resources

Jason Wu, Yuyang Yuan, Kang Yang, Lance M. Kaplan, Mani Srivastava

Keywords: multimodal deep learning, dynamic neural networks, compute limited systems

TL;DR: ADMN enables layer-wise allocation of resources among modalities at inference time according to modality quality for a fixed resource budget.

Abstract: Multimodal deep learning systems are deployed in dynamic scenarios due to the robustness afforded by multiple sensing modalities. Nevertheless, they struggle with varying compute resource availability (due to multi-tenancy, device heterogeneity, etc.) and fluctuating quality of inputs (from sensor feed corruption, environmental noise, etc.). Statically provisioned multimodal systems cannot adapt when compute resources change over time, while existing dynamic networks struggle with strict compute budgets. Additionally, both systems often neglect the impact of variations in modality quality. Consequently, modalities suffering substantial corruption may needlessly consume resources better allocated towards other modalities. We propose ADMN, a layer-wise Adaptive Depth Multimodal Network capable of tackling both challenges - it adjusts the total number of active layers across all modalities to meet compute resource constraints, and continually reallocates layers across input modalities according to their modality quality. Our evaluations showcase ADMN can match the accuracy of state-of-the-art networks while reducing up to 75% of their floating-point operations.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 9553