Holographic Memory for Zero-Shot Compositional Reasoning in Knowledge Graphs: A Mechanistic Study of Where and Why It Fails
arXiv:2606.24948v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) models predict single-hop links well but have no mechanism for zero-shot compositional queries: multi-hop questions whose relation chains never appeared during training. Holographic Reduced Representations (HRR), which bind and unbind symbols via circular convolution, are a theoretically attractive candidate, since binding is approximately invertible and associative. We test whether this promise holds. We study two h...
arXiv cs.LG
·Randhir Kumar
·
// relacionados
Leia também
Blog
Amazon ups India bet with fresh $13B AI infrastructure investment
Editorial
Jalapeño: a OpenAI projeta seu primeiro chip de inferência — e usou IA para fazer isso em 9 meses
Editorial
SkillOpt: como ensinar agentes de IA a melhorar suas próprias habilidades — +23 pontos em GPT-5.5
Blog