Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation
- URL: http://arxiv.org/abs/2404.14271v1
- Date: Mon, 22 Apr 2024 15:16:59 GMT
- Title: Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation
- Authors: Paulo Yanez Sarmiento, Simon Witzke, Nadja Klein, Bernhard Y. Renard,
- Abstract summary: We present a modification of the widely used explanation method layer-wise relevance propagation.
Our approach enforces sparsity directly by pruning the relevance propagation for the different layers.
We show that our modification indeed leads to noise reduction and concentrates relevance on the most important features compared to the baseline.
- Score: 1.593690982728631
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Explainability is a key component in many applications involving deep neural networks (DNNs). However, current explanation methods for DNNs commonly leave it to the human observer to distinguish relevant explanations from spurious noise. This is not feasible anymore when going from easily human-accessible data such as images to more complex data such as genome sequences. To facilitate the accessibility of DNN outputs from such complex data and to increase explainability, we present a modification of the widely used explanation method layer-wise relevance propagation. Our approach enforces sparsity directly by pruning the relevance propagation for the different layers. Thereby, we achieve sparser relevance attributions for the input features as well as for the intermediate layers. As the relevance propagation is input-specific, we aim to prune the relevance propagation rather than the underlying model architecture. This allows to prune different neurons for different inputs and hence, might be more appropriate to the local nature of explanation methods. To demonstrate the efficacy of our method, we evaluate it on two types of data, images and genomic sequences. We show that our modification indeed leads to noise reduction and concentrates relevance on the most important features compared to the baseline.
Related papers
- Deep Graph Neural Networks via Flexible Subgraph Aggregation [50.034313206471694]
Graph neural networks (GNNs) can learn from graph-structured data and learn the representation of nodes through aggregating neighborhood information.
In this paper, we evaluate the expressive power of GNNs from the perspective of subgraph aggregation.
We propose a sampling-based node-level residual module (SNR) that can achieve a more flexible utilization of different hops of subgraph aggregation.
arXiv Detail & Related papers (2023-05-09T12:03:42Z) - An Exploration of Conditioning Methods in Graph Neural Networks [8.532288965425805]
In computational tasks such as physics and chemistry usage of edge attributes such as relative position or distance proved to be essential.
We consider three types of conditioning; weak, strong, and pure, which respectively relate to concatenation-based conditioning, gating, and transformations that are causally dependent on the attributes.
This categorization provides a unifying viewpoint on different classes of GNNs, from separable convolutions to various forms of message passing networks.
arXiv Detail & Related papers (2023-05-03T07:14:12Z) - Deep Architecture Connectivity Matters for Its Convergence: A
Fine-Grained Analysis [94.64007376939735]
We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training.
We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
arXiv Detail & Related papers (2022-05-11T17:43:54Z) - Decomposing neural networks as mappings of correlation functions [57.52754806616669]
We study the mapping between probability distributions implemented by a deep feed-forward network.
We identify essential statistics in the data, as well as different information representations that can be used by neural networks.
arXiv Detail & Related papers (2022-02-10T09:30:31Z) - Discovering Invariant Rationales for Graph Neural Networks [104.61908788639052]
Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input graph's features.
We propose a new strategy of discovering invariant rationale (DIR) to construct intrinsically interpretable GNNs.
arXiv Detail & Related papers (2022-01-30T16:43:40Z) - DisenHAN: Disentangled Heterogeneous Graph Attention Network for
Recommendation [11.120241862037911]
Heterogeneous information network has been widely used to alleviate sparsity and cold start problems in recommender systems.
We propose a novel disentangled heterogeneous graph attention network DisenHAN for top-$N$ recommendation.
arXiv Detail & Related papers (2021-06-21T06:26:10Z) - Enhance Information Propagation for Graph Neural Network by
Heterogeneous Aggregations [7.3136594018091134]
Graph neural networks are emerging as continuation of deep learning success w.r.t. graph data.
We propose to enhance information propagation among GNN layers by combining heterogeneous aggregations.
We empirically validate the effectiveness of HAG-Net on a number of graph classification benchmarks.
arXiv Detail & Related papers (2021-02-08T08:57:56Z) - Interpreting Deep Neural Networks with Relative Sectional Propagation by
Analyzing Comparative Gradients and Hostile Activations [37.11665902583138]
We propose a new attribution method, Relative Sectional Propagation (RSP), for decomposing the output predictions of Deep Neural Networks (DNNs)
We define hostile factor as an element that interferes with finding the attributions of the target and propagates it in a distinguishable way to overcome the non-suppressed nature of activated neurons.
Our method makes it possible to decompose the predictions of DNNs with clearer class-discriminativeness and detailed elucidations of activation neurons compared to the conventional attribution methods.
arXiv Detail & Related papers (2020-12-07T03:11:07Z) - Spatio-Temporal Inception Graph Convolutional Networks for
Skeleton-Based Action Recognition [126.51241919472356]
We design a simple and highly modularized graph convolutional network architecture for skeleton-based action recognition.
Our network is constructed by repeating a building block that aggregates multi-granularity information from both the spatial and temporal paths.
arXiv Detail & Related papers (2020-11-26T14:43:04Z) - GCN for HIN via Implicit Utilization of Attention and Meta-paths [104.24467864133942]
Heterogeneous information network (HIN) embedding aims to map the structure and semantic information in a HIN to distributed representations.
We propose a novel neural network method via implicitly utilizing attention and meta-paths.
We first use the multi-layer graph convolutional network (GCN) framework, which performs a discriminative aggregation at each layer.
We then give an effective relaxation and improvement via introducing a new propagation operation which can be separated from aggregation.
arXiv Detail & Related papers (2020-07-06T11:09:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.