论文标题
使用能力网络有效且可解释的信息聚合
Effective and Interpretable Information Aggregation with Capacity Networks
论文作者
论文摘要
如何从多个实例中汇总信息是一个关键问题多重实例学习。先前的神经模型实施了众所周知的编码器策略的不同变体，根据该变量，所有输入特征均编码单个高维嵌入，然后将其解码以生成输出。在这项工作中，受Choquet能力的启发，我们提出了能力网络。与编码器解码器不同，容量网络会生成多个可解释的中间结果，这些结果可以在语义上有意义的空间中汇总以获得最终输出。我们的实验表明，实施这种简单的电感偏置会导致在广泛的实验中对不同编码器架构的改进。此外，可解释的中间结果使能力网络可通过设计来解释，从而允许语义上有意义的检查，评估和正规化网络内部设备。
How to aggregate information from multiple instances is a key question multiple instance learning. Prior neural models implement different variants of the well-known encoder-decoder strategy according to which all input features are encoded a single, high-dimensional embedding which is then decoded to generate an output. In this work, inspired by Choquet capacities, we propose Capacity networks. Unlike encoder-decoders, Capacity networks generate multiple interpretable intermediate results which can be aggregated in a semantically meaningful space to obtain the final output. Our experiments show that implementing this simple inductive bias leads to improvements over different encoder-decoder architectures in a wide range of experiments. Moreover, the interpretable intermediate results make Capacity networks interpretable by design, which allows a semantically meaningful inspection, evaluation, and regularization of the network internals.
