Columnar-Embedder：一种受生物启发的皮层架构，用于二进制稀疏分布式图表示
Columnar-Embedder: A Biologically Inspired Cortical Architecture for Binary Sparse Distributed Graph Representations
AI总结：
本文提出受生物启发的 Columnar-Embedder 架构，用局部 BCM 赫布规则结合 PPMI 学习图节点的二进制 SDR，在五个图基准上性能与实值密集嵌入相当，且抗遗忘、抗噪、鲁棒性强。
AI中文摘要：
图嵌入技术因图的非欧几里得性质，难以找到能捕捉图实体结构角色与同质性的代表性描述。传统图嵌入方法通过随机游走与图神经网络（GNN）实现最优性能，但这些方法是直推式的，需通过 softmax 或密集表示进行昂贵的全局优化，且采用梯度下降端到端训练。其他 GNN 变体虽可映射到未见节点，仍依赖迭代消息传递与反向传播，导致计算和内存成本高昂。相反，哺乳动物皮层通过学习将输入模式流映射为紧凑表示供下游区域使用，解决结构相似问题。本文提出受生物启发的 Columnar-Embedder 架构，用于学习图节点的二进制稀疏分布式表示（SDR）。学习由局部 Bienenstock-Cooper-Munro（BCM）赫布规则驱动，该规则由从在线随机游走流计算的正点互信息（PPMI）调制。从无标签、无反向传播、无监督的流式随机游走对进行持续学习，使该架构天然具备对抗灾难性遗忘的能力。在五个图基准测试中，SDR 在节点分类与链接预测任务上的性能与实值密集嵌入相当，同时该架构具备可移植性、抗噪性及对数据损坏的鲁棒性。
英文摘要：
Finding a representative description of graph entities that captures their structural roles and homophily is a challenging goal for graph embedding techniques due to the non-Euclidean nature of graphs. Traditionally, Graph embeddings achieve top performance via random-walk methods and graph neural networks. However, these methods are transductive and utilize an expensive global optimization via softmax or a dense representation trained in an end-to-end pipeline with gradient descent. Nonetheless, other variants of GNNs can map to unseen nodes; they still rely on iterative message passing and backpropagation, incurring high computational and memory costs. Conversely, the mammalian cortex solves structurally similar problems by learning to map its input stream of patterns into a compact representation for downstream regions. We present the biologically inspired Columnar-Embedder architecture for learning binary Sparse Distributed Representations (SDRs) of graph nodes. The learning is driven by a local Bienenstock-Cooper-Munro (BCM) Hebbian rule modulated by positive pointwise mutual information (PPMI) computed from online streams of random walks. Continuous learning from streaming random-walk pairs without labels, backpropagation, or supervision enables the architecture to exhibit natural resistance to catastrophic forgetting. Across five graph benchmarks, the performance of SDRs is competitive with that of real-valued dense embeddings on node classification and link prediction, while the architecture exhibits portability, resilience to noise, and robustness to data corruption.
