可解释的CNN

2017 年 10 月 5 日 CreateAMind
可解释的CNN


Interpretable Convolutional Neural Networks

Quanshi Zhang, Ying Nian Wu, Song-Chun Zhu

(Submitted on 2 Oct 2017)

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high conv-layer represents a certain object part. We do not need any annotations of object parts or textures to supervise the learning process. Instead, the interpretable CNN automatically assigns each filter in a high conv-layer with an object part during the learning process. Our method can be applied to different types of CNNs with different structures. The clear knowledge representation in an interpretable CNN can help people understand the logics inside a CNN, i.e., based on which patterns the CNN makes the decision. Experiments showed that filters in an interpretable CNN were more semantically meaningful than those in traditional CNNs. 



https://arxiv.org/abs/1710.00935



登录查看更多
11

相关内容

在深度学习中,卷积神经网络(CNN或ConvNet)是一类深度神经网络,最常用于分析视觉图像。基于它们的共享权重架构和平移不变性特征,它们也被称为位移不变或空间不变的人工神经网络(SIANN)。它们在图像和视频识别,推荐系统,图像分类,医学图像分析,自然语言处理,和财务时间序列中都有应用。

知识荟萃

精品入门和进阶教程、论文和代码整理等

更多

查看相关VIP内容、论文、资讯等

This paper proposes a generic method to learn interpretable convolutional filters in a deep convolutional neural network (CNN) for object classification, where each interpretable filter encodes features of a specific object part. Our method does not require additional annotations of object parts or textures for supervision. Instead, we use the same training data as traditional CNNs. Our method automatically assigns each interpretable filter in a high conv-layer with an object part of a certain category during the learning process. Such explicit knowledge representations in conv-layers of CNN help people clarify the logic encoded in the CNN, i.e., answering what patterns the CNN extracts from an input image and uses for prediction. We have tested our method using different benchmark CNNs with various structures to demonstrate the broad applicability of our method. Experiments have shown that our interpretable filters are much more semantically meaningful than traditional filters.

0
14
下载
预览

This paper introduces a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside conv-layers of a pre-trained CNN. Each filter in a conv-layer of a CNN for object classification usually represents a mixture of object parts. We develop a simple yet effective method to disentangle object-part pattern components from each filter. We construct an explanatory graph to organize the mined part patterns, where a node represents a part pattern, and each edge encodes co-activation relationships and spatial relationships between patterns. More crucially, given a pre-trained CNN, the explanatory graph is learned without a need of annotating object parts. Experiments show that each graph node consistently represented the same object part through different images, which boosted the transferability of CNN features. We transferred part patterns in the explanatory graph to the task of part localization, and our method significantly outperformed other approaches.

0
4
下载
预览

Incorporating knowledge graph into recommender systems has attracted increasing attention in recent years. By exploring the interlinks within a knowledge graph, the connectivity between users and items can be discovered as paths, which provide rich and complementary information to user-item interactions. Such connectivity not only reveals the semantics of entities and relations, but also helps to comprehend a user's interest. However, existing efforts have not fully explored this connectivity to infer user preferences, especially in terms of modeling the sequential dependencies within and holistic semantics of a path. In this paper, we contribute a new model named Knowledge-aware Path Recurrent Network (KPRN) to exploit knowledge graph for recommendation. KPRN can generate path representations by composing the semantics of both entities and relations. By leveraging the sequential dependencies within a path, we allow effective reasoning on paths to infer the underlying rationale of a user-item interaction. Furthermore, we design a new weighted pooling operation to discriminate the strengths of different paths in connecting a user with an item, endowing our model with a certain level of explainability. We conduct extensive experiments on two datasets about movie and music, demonstrating significant improvements over state-of-the-art solutions Collaborative Knowledge Base Embedding and Neural Factorization Machine.

0
7
下载
预览

The potential of graph convolutional neural networks for the task of zero-shot learning has been demonstrated recently. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization to new classes when faced with a lack of data. However, knowledge from distant nodes can get diluted when propagating through intermediate nodes, because current approaches to zero-shot learning use graph propagation schemes that perform Laplacian smoothing at each layer. We show that extensive smoothing does not help the task of regressing classifier weights in zero-shot learning. In order to still incorporate information from distant nodes and utilize the graph structure, we propose an Attentive Dense Graph Propagation Module (ADGPM). ADGPM allows us to exploit the hierarchical graph structure of the knowledge graph through additional connections. These connections are added based on a node's relationship to its ancestors and descendants and an attention scheme is further used to weigh their contribution depending on the distance to the node. Finally, we illustrate that finetuning of the feature representation after training the ADGPM leads to considerable improvements. Our method achieves competitive results, outperforming previous zero-shot learning approaches.

0
14
下载
预览

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high conv-layer represents a certain object part. We do not need any annotations of object parts or textures to supervise the learning process. Instead, the interpretable CNN automatically assigns each filter in a high conv-layer with an object part during the learning process. Our method can be applied to different types of CNNs with different structures. The clear knowledge representation in an interpretable CNN can help people understand the logics inside a CNN, i.e., based on which patterns the CNN makes the decision. Experiments showed that filters in an interpretable CNN were more semantically meaningful than those in traditional CNNs.

0
14
下载
预览

This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance in various tasks, the interpretability is always the Achilles' heel of deep neural networks. At present, deep neural networks obtain high discrimination power at the cost of low interpretability of their black-box representations. We believe that high model interpretability may help people to break several bottlenecks of deep learning, e.g., learning from very few annotations, learning via human-computer communications at the semantic level, and semantically debugging network representations. We focus on convolutional neural networks (CNNs), and we revisit the visualization of CNN representations, methods of diagnosing representations of pre-trained CNNs, approaches for disentangling pre-trained CNN representations, learning of CNNs with disentangled representations, and middle-to-end learning based on model interpretability. Finally, we discuss prospective trends in explainable artificial intelligence.

0
12
下载
预览

Online news recommender systems aim to address the information explosion of news and make personalized recommendation for users. In general, news language is highly condensed, full of knowledge entities and common sense. However, existing methods are unaware of such external knowledge and cannot fully discover latent knowledge-level connections among news. The recommended results for a user are consequently limited to simple patterns and cannot be extended reasonably. Moreover, news recommendation also faces the challenges of high time-sensitivity of news and dynamic diversity of users' interests. To solve the above problems, in this paper, we propose a deep knowledge-aware network (DKN) that incorporates knowledge graph representation into news recommendation. DKN is a content-based deep recommendation framework for click-through rate prediction. The key component of DKN is a multi-channel and word-entity-aligned knowledge-aware convolutional neural network (KCNN) that fuses semantic-level and knowledge-level representations of news. KCNN treats words and entities as multiple channels, and explicitly keeps their alignment relationship during convolution. In addition, to address users' diverse interests, we also design an attention module in DKN to dynamically aggregate a user's history with respect to current candidate news. Through extensive experiments on a real online news platform, we demonstrate that DKN achieves substantial gains over state-of-the-art deep recommendation models. We also validate the efficacy of the usage of knowledge in DKN.

0
18
下载
预览

This paper learns a graphical model, namely an explanatory graph, which reveals the knowledge hierarchy hidden inside a pre-trained CNN. Considering that each filter in a conv-layer of a pre-trained CNN usually represents a mixture of object parts, we propose a simple yet efficient method to automatically disentangles different part patterns from each filter, and construct an explanatory graph. In the explanatory graph, each node represents a part pattern, and each edge encodes co-activation relationships and spatial relationships between patterns. More importantly, we learn the explanatory graph for a pre-trained CNN in an unsupervised manner, i.e., without a need of annotating object parts. Experiments show that each graph node consistently represents the same object part through different images. We transfer part patterns in the explanatory graph to the task of part localization, and our method significantly outperforms other approaches.

0
8
下载
预览
小贴士
相关资讯
AI可解释性文献列表
专知
35+阅读 · 2019年10月7日
强化学习三篇论文 避免遗忘等
CreateAMind
10+阅读 · 2019年5月24日
卷积神经网络的最佳解释!
专知
11+阅读 · 2018年5月1日
【CNN】一文读懂卷积神经网络CNN
产业智能官
11+阅读 · 2018年1月2日
【论文】深度学习的数学解释
机器学习研究会
8+阅读 · 2017年12月15日
【推荐】深度学习目标检测全面综述
机器学习研究会
17+阅读 · 2017年9月13日
【推荐】用Tensorflow理解LSTM
机器学习研究会
25+阅读 · 2017年9月11日
【推荐】TensorFlow手把手CNN实践指南
机器学习研究会
5+阅读 · 2017年8月17日
相关论文
Interpretable CNNs for Object Classification
Quanshi Zhang,Xin Wang,Ying Nian Wu,Huilin Zhou,Song-Chun Zhu
14+阅读 · 2020年3月12日
Explanatory Graphs for CNNs
Quanshi Zhang,Xin Wang,Ruiming Cao,Ying Nian Wu,Feng Shi,Song-Chun Zhu
4+阅读 · 2018年12月18日
Xiang Wang,Dingxian Wang,Canran Xu,Xiangnan He,Yixin Cao,Tat-Seng Chua
7+阅读 · 2018年11月12日
Bo-Jian Hou,Zhi-Hua Zhou
16+阅读 · 2018年10月25日
Michael Kampffmeyer,Yinbo Chen,Xiaodan Liang,Hao Wang,Yujia Zhang,Eric P. Xing
14+阅读 · 2018年5月31日
Yongfeng Zhang,Qingyao Ai,Xu Chen,Pengfei Wang
21+阅读 · 2018年3月22日
Quanshi Zhang,Ying Nian Wu,Song-Chun Zhu
14+阅读 · 2018年2月14日
Quanshi Zhang,Song-Chun Zhu
12+阅读 · 2018年2月7日
Hongwei Wang,Fuzheng Zhang,Xing Xie,Minyi Guo
18+阅读 · 2018年1月30日
Quanshi Zhang,Ruiming Cao,Feng Shi,Ying Nian Wu,Song-Chun Zhu
8+阅读 · 2017年11月22日
Top