0 评论 (0 评论)0 反应 (0 反应)0 负责人 (0 负责人)Python19,985 star (19,985 star)3,514 fork (3,514 fork)batch import
documentationhelp wantednn
- 议题类型
- feature
- 前置要求
- 无
- 研究方向
- The issue requests the ability to customize aggregation functions in message passing layers. Contributors should review the existing message passing base class (e.g., torch geometric.nn.conv.MessagePassing) to understand current aggregation options (add, mean, max, etc.). A possible implementation could involve allowing users to pass custom aggregation functions as arguments to layers, similar to how aggregation is currently handled via 'aggr' parameter. Maintainers likely expect a discussion on design before implementation.