Firstly, SGTs ( i.e., simple GNNs) are still powerful and can "distinguish almost all non-isomorphic graphs" [ VQ-V AE (Table 3b) emphasizes the impact of pretraining methods on the tokenizer's performance. We leave the investigation of how to effectively pretrain GNN-based tokenizers as future works. We have included the literature review of MGM in the main body of the paper. However, a closer inspection reveals several critical distinctions between MGM and these methods. Finally, MGM employs remask decoding to constrain the encoder's ability on This code uses a single-layer SGT of GIN as an example.

While large language models have demonstrated this ability, how in-context learning could be performed over graphs is unexplored. In this paper, we develop Pr etraining O ver D iverse I n-Context G raph S y stems (PRODIGY), the first pretraining framework that enables in-context learning over graphs.

In this work we focus on one primary use case: neuroprosthetics powered by intracortical brain computer interfaces (iBCIs). With electrical recordings of just dozens to hundreds of channels of neuronal population spiking activity, today's iBCIs can relate this observed neural activity to behavioral intent, achieving impressive milestones such as high-speed speech decoding [