Sign Rank Limitations for Attention-Based Graph Decoders
CoRR(2024)
摘要
Inner product-based decoders are among the most influential frameworks used
to extract meaningful data from latent embeddings. However, such decoders have
shown limitations in representation capacity in numerous works within the
literature, which have been particularly notable in graph reconstruction
problems. In this paper, we provide the first theoretical elucidation of this
pervasive phenomenon in graph data, and suggest straightforward modifications
to circumvent this issue without deviating from the inner product framework.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要