AI 中文总结
研究谱高阶神经网络的表达能力界限，提出利用谱属性的新参数化方法，通过权重共享降低计算成本，在N位奇偶校验任务上评估该框架，证明其具有通用且可调的假设空间。
AI 中文摘要
神经超图是现代机器学习中参考模型神经网络的自然推广。然而，其部署要求苛刻，加权超边数量会导致棘手的参数爆炸。最近提出了一种利用神经超图谱属性的新参数化方法，可通过权重共享方案循环利用参数，从而显著降低计算成本。在谱高阶架构上进行的初步测试表明性能和可解释性都有显著改善。在此基础上，我们通过在N位奇偶校验任务上评估谱高阶框架来推进基准测试工作，该任务是一个公认的特别具有挑战性的测试平台。我们将令人信服地论证，谱高阶神经网络（SHONNs）拥有一个通用且高度可调的假设空间。
英文摘要
Neural hypergraphs are a natural generalization of neural networks, the reference models in modern machine learning. Yet, their deployment has proven demanding: the number of weighted hyperedges required leads to an intractable parameter explosion. However, a novel parametrization that leverages spectral attributes for neural hypergraphs has been recently proposed, that enables to recycle parameters via a weight sharing scheme and consequently yields a significant reduction of the associated computational cost. Preliminary tests carried out on spectral higher-order architectures pointed to meaningful improvements in both performance and interpretability. Building on these results, we advance the benchmarking efforts by evaluating the spectral higher order framework on N-bit parity tasks, a well-established testbed known to be particularly challenging. As we will convincingly argue, Spectral Higher-Order Neural Networks (SHONNs) possess a versatile and highly tunable hypothesis space.
