Revisiting Attention Weights as Explanations from an Information Theoretic Perspective

• URL: http://arxiv.org/abs/2211.07714v1
• Date: Mon, 31 Oct 2022 12:53:20 GMT
• Title: Revisiting Attention Weights as Explanations from an Information Theoretic Perspective
• Authors: Bingyang Wen, K.P. Subbalakshmi, Fan Yang
• Abstract summary: We show that attention mechanisms have the potential to function as a shortcut to model explanations when they are carefully combined with other model elements. Our findings indicate that attention mechanisms do have the potential to function as a shortcut to model explanations when they are carefully combined with other model elements.
• Score: 4.499369811647602
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Attention mechanisms have recently demonstrated impressive performance on a range of NLP tasks, and attention scores are often used as a proxy for model explainability. However, there is a debate on whether attention weights can, in fact, be used to identify the most important inputs to a model. We approach this question from an information theoretic perspective by measuring the mutual information between the model output and the hidden states. From extensive experiments, we draw the following conclusions: (i) Additive and Deep attention mechanisms are likely to be better at preserving the information between the hidden states and the model output (compared to Scaled Dot-product); (ii) ablation studies indicate that Additive attention can actively learn to explain the importance of its input hidden representations; (iii) when attention values are nearly the same, the rank order of attention values is not consistent with the rank order of the mutual information(iv) Using Gumbel-Softmax with a temperature lower than one, tends to produce a more skewed attention score distribution compared to softmax and hence is a better choice for explainable design; (v) some building blocks are better at preserving the correlation between the ordered list of mutual information and attention weights order (for e.g., the combination of BiLSTM encoder and Additive attention). Our findings indicate that attention mechanisms do have the potential to function as a shortcut to model explanations when they are carefully combined with other model elements.

Related papers

• Naturalness of Attention: Revisiting Attention in Code Language Models [3.756550107432323]
  Language models for code such as CodeBERT offer the capability to learn advanced source code representation, but their opacity poses barriers to understanding of captured properties. This study aims to shed some light on the previously ignored factors of the attention mechanism beyond the attention weights.
  arXiv  Detail & Related papers  (2023-11-22T16:34:12Z)
• Message Intercommunication for Inductive Relation Reasoning [49.731293143079455]
  We develop a novel inductive relation reasoning model called MINES. We introduce a Message Intercommunication mechanism on the Neighbor-Enhanced Subgraph. Our experiments show that MINES outperforms existing state-of-the-art models.
  arXiv  Detail & Related papers  (2023-05-23T13:51:46Z)
• Guiding Visual Question Answering with Attention Priors [76.21671164766073]
  We propose to guide the attention mechanism using explicit linguistic-visual grounding. This grounding is derived by connecting structured linguistic concepts in the query to their referents among the visual objects. The resultant algorithm is capable of probing attention-based reasoning models, injecting relevant associative knowledge, and regulating the core reasoning process.
  arXiv  Detail & Related papers  (2022-05-25T09:53:47Z)
• Attention cannot be an Explanation [99.37090317971312]
  We ask how effective are attention based explanations in increasing human trust and reliance in the underlying models? We perform extensive human study experiments that aim to qualitatively and quantitatively assess the degree to which attention based explanations are suitable. Our experiment results show that attention cannot be used as an explanation.
  arXiv  Detail & Related papers  (2022-01-26T21:34:05Z)
• How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction [66.09605613944201]
  We quantitatively evaluate the effect of attention and Knowledge Graph on bag-level relation extraction (RE) We find that (1) higher attention accuracy may lead to worse performance as it may harm the model's ability to extract entity mention features; (2) the performance of attention is largely influenced by various noise distribution patterns; and (3) KG-enhanced attention indeed improves RE performance, while not through enhanced attention but by incorporating entity prior.
  arXiv  Detail & Related papers  (2021-07-26T09:38:28Z)
• Improve the Interpretability of Attention: A Fast, Accurate, and Interpretable High-Resolution Attention Model [6.906621279967867]
  We propose a novel Bilinear Representative Non-Parametric Attention (BR-NPA) strategy that captures the task-relevant human-interpretable information. The proposed model can be easily adapted in a wide variety of modern deep models, where classification is involved. It is also more accurate, faster, and with a smaller memory footprint than usual neural attention modules.
  arXiv  Detail & Related papers  (2021-06-04T15:57:37Z)
• Is Sparse Attention more Interpretable? [52.85910570651047]
  We investigate how sparsity affects our ability to use attention as an explainability tool. We find that only a weak relationship between inputs and co-indexed intermediate representations exists -- under sparse attention. We observe in this setting that inducing sparsity may make it less plausible that attention can be used as a tool for understanding model behavior.
  arXiv  Detail & Related papers  (2021-06-02T11:42:56Z)
• SparseBERT: Rethinking the Importance Analysis in Self-attention [107.68072039537311]
  Transformer-based models are popular for natural language processing (NLP) tasks due to its powerful capacity. Attention map visualization of a pre-trained model is one direct method for understanding self-attention mechanism. We propose a Differentiable Attention Mask (DAM) algorithm, which can be also applied in guidance of SparseBERT design.
  arXiv  Detail & Related papers  (2021-02-25T14:13:44Z)
• Attention improves concentration when learning node embeddings [1.2233362977312945]
  Given nodes labelled with search query text, we want to predict links to related queries that share products. Experiments with a range of deep neural architectures show that simple feedforward networks with an attention mechanism perform best for learning embeddings. We propose an analytically tractable model of query generation, AttEST, that views both products and the query text as vectors embedded in a latent space.
  arXiv  Detail & Related papers  (2020-06-11T21:21:12Z)

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.