# MetaPOCS: Meta-Learned Multi-Exit Unfolding for Budget-Aware Seismic Data Interpolation

DevFeed: [MetaPOCS: Meta-Learned Multi-Exit Unfolding for Budget-Aware Seismic Data Interpolation](<https://devfeed.tech/articles/metapocs-meta-learned-multi-exit-unfolding-for-budget-aware-seismic-data-interpolation-114709.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02478>)

Author: Baisong Jiang, Chunxia Zhang, Xiaoli Wei, Anxiang Di, Nanqi Zhao, Deng Xiong

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [quantization](<https://devfeed.tech/topics/quantization.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [acquisition](<https://devfeed.tech/tags/acquisition.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [budget](<https://devfeed.tech/tags/budget.md>), [checkpoint](<https://devfeed.tech/tags/checkpoint.md>), [comparisons](<https://devfeed.tech/tags/comparisons.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [diagnostics](<https://devfeed.tech/tags/diagnostics.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [exit](<https://devfeed.tech/tags/exit.md>), [fixed](<https://devfeed.tech/tags/fixed.md>), [framework](<https://devfeed.tech/tags/framework.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [imaging](<https://devfeed.tech/tags/imaging.md>), [inference](<https://devfeed.tech/tags/inference.md>), [intermediate](<https://devfeed.tech/tags/intermediate.md>), [latency](<https://devfeed.tech/tags/latency.md>), [mechanism](<https://devfeed.tech/tags/mechanism.md>), [meta](<https://devfeed.tech/tags/meta.md>)

## AI overview

MetaPOCS addresses seismic interpolation under variable compute budgets by training intermediate exits of a spatial-spectral POCS unfolding network while preserving acquired traces at every exit. From a common initialization, its Meta-GF procedure builds exit-specific parameter updates and learns tensor-varying fusion weights with an equal-exit outer objective; the derived hypergradient describes how that objective reallocates competing updates, unlike scalar loss reweighting. A single checkpoint then offers multiple reconstruction budgets through a latency-calibrated exit policy. The abstract says evaluation pairs matched-cost interpolation comparisons and finite-update diagnostics with a fixed reverse-time-migration operator to assess waveform and imaging fidelity.

## Source excerpt

arXiv:2611.02478v1 Announce Type: new Abstract: Seismic data interpolation must reconcile reconstruction fidelity with the computational budgets of acquisition quality control and subsequent imaging. Fixed-depth unfolding networks are optimized for a single operating point, whereas their intermediate estimates may be insufficiently trained for early deployment. We present MetaPOCS, a meta-learned multi-exit unfolding framework for budget-aware seismic interpolation. Building on a spatial--spectral POCS reconstruction backbone, MetaPOCS supervises intermediate stages and preserves the acquired traces at every exit. A Meta-GF-based optimization procedure constructs exit-oriented parameter displacements from a common initialization and learns their fusion weights through an equal-exit outer objective. The weights vary across parameter tensors and respect the nested support of the reconstruction stages. We derive the resulting fusion hypergradient to characterize how the outer objective reallocates competing updates, and distinguish this mechanism from scalar loss reweighting. At inference, one checkpoint provides a set of reconstruction budgets through a latency-calibrated exit policy. The evaluation framework couples matched-cost interpolation comparisons with finite-update diagnostics and a fixed reverse-time-migration operator, connecting multi-exit optimization to waveform and imaging fidelity. MetaPOCS thus provides a unified formulation for studying the reconstruction--computation trade-off of seismic unfolding across deployment budgets.