Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
This work addresses a specific bottleneck in MPGNNs for graph modeling, offering a plug-and-play solution that improves performance in downstream tasks.
The paper tackles the limitation of sum-based aggregators in Message Passing Graph Neural Networks (MPGNNs) by introducing Sequential Signal Mixing Aggregation (SSMA), which enhances feature mixing among neighbors and achieves new state-of-the-art results across various benchmarks.
Message Passing Graph Neural Networks (MPGNNs) have emerged as the preferred method for modeling complex interactions across diverse graph entities. While the theory of such models is well understood, their aggregation module has not received sufficient attention. Sum-based aggregators have solid theoretical foundations regarding their separation capabilities. However, practitioners often prefer using more complex aggregations and mixtures of diverse aggregations. In this work, we unveil a possible explanation for this gap. We claim that sum-based aggregators fail to "mix" features belonging to distinct neighbors, preventing them from succeeding at downstream tasks. To this end, we introduce Sequential Signal Mixing Aggregation (SSMA), a novel plug-and-play aggregation for MPGNNs. SSMA treats the neighbor features as 2D discrete signals and sequentially convolves them, inherently enhancing the ability to mix features attributed to distinct neighbors. By performing extensive experiments, we show that when combining SSMA with well-established MPGNN architectures, we achieve substantial performance gains across various benchmarks, achieving new state-of-the-art results in many settings. We published our code at \url{https://almogdavid.github.io/SSMA/}