Asymmetric feature interaction for interpreting model predictions

• URL: http://arxiv.org/abs/2305.07224v4
• Date: Thu, 26 Oct 2023 02:32:54 GMT
• Title: Asymmetric feature interaction for interpreting model predictions
• Authors: Xiaolei Lu, Jianghong Ma, Haode Zhang
• Abstract summary: In natural language processing, deep neural networks (DNNs) could model complex interactions between context. We propose an asymmetric feature interaction attribution model that aims to explore asymmetric higher-order feature interactions. Experimental results on two sentiment classification datasets show the superiority of our model against the state-of-the-art feature interaction attribution methods.
• Score: 13.934784414106087
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In natural language processing (NLP), deep neural networks (DNNs) could model complex interactions between context and have achieved impressive results on a range of NLP tasks. Prior works on feature interaction attribution mainly focus on studying symmetric interaction that only explains the additional influence of a set of words in combination, which fails to capture asymmetric influence that contributes to model prediction. In this work, we propose an asymmetric feature interaction attribution explanation model that aims to explore asymmetric higher-order feature interactions in the inference of deep neural NLP models. By representing our explanation with an directed interaction graph, we experimentally demonstrate interpretability of the graph to discover asymmetric feature interactions. Experimental results on two sentiment classification datasets show the superiority of our model against the state-of-the-art feature interaction attribution methods in identifying influential features for model predictions. Our code is available at https://github.com/StillLu/ASIV.

Related papers

• GraphGI:A GNN Explanation Method using Game Interaction [5.149896909638598]
  Graph Neural Networks (GNNs) have garnered significant attention and have been extensively utilized across various domains. Current graph explanation techniques focus on identifying key nodes or edges, attributing the critical data features that drive model predictions. We propose a novel explanatory method GraphGI, which identifies the coalition with the highest interaction strength and presents it as an explanatory subgraph.
  arXiv  Detail & Related papers  (2024-09-24T03:24:31Z)
• On the Joint Interaction of Models, Data, and Features [82.60073661644435]
  We introduce a new tool, the interaction tensor, for empirically analyzing the interaction between data and model through features. Based on these observations, we propose a conceptual framework for feature learning. Under this framework, the expected accuracy for a single hypothesis and agreement for a pair of hypotheses can both be derived in closed-form.
  arXiv  Detail & Related papers  (2023-06-07T21:35:26Z)
• Exploring the cloud of feature interaction scores in a Rashomon set [17.775145325515993]
  We introduce the feature interaction score (FIS) in the context of a Rashomon set. We demonstrate the properties of the FIS via synthetic data and draw connections to other areas of statistics. Our results suggest that the proposed FIS can provide valuable insights into the nature of feature interactions in machine learning models.
  arXiv  Detail & Related papers  (2023-05-17T13:05:26Z)
• EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning [83.11657818251447]
  We propose EqMotion, an efficient equivariant motion prediction model with invariant interaction reasoning. We conduct experiments for the proposed model on four distinct scenarios: particle dynamics, molecule dynamics, human skeleton motion prediction and pedestrian trajectory prediction. Our method achieves state-of-the-art prediction performances on all the four tasks, improving by 24.0/30.1/8.6/9.2%.
  arXiv  Detail & Related papers  (2023-03-20T05:23:46Z)
• Modeling Implicit Bias with Fuzzy Cognitive Maps [0.0]
  This paper presents a Fuzzy Cognitive Map model to quantify implicit bias in structured datasets. We introduce a new reasoning mechanism equipped with a normalization-like transfer function that prevents neurons from saturating.
  arXiv  Detail & Related papers  (2021-12-23T17:04:12Z)
• Towards Interaction Detection Using Topological Analysis on Neural Networks [55.74562391439507]
  In neural networks, any interacting features must follow a strongly weighted connection to common hidden units. We propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology. A Persistence Interaction detection(PID) algorithm is developed to efficiently detect interactions.
  arXiv  Detail & Related papers  (2020-10-25T02:15:24Z)
• Explaining and Improving Model Behavior with k Nearest Neighbor Representations [107.24850861390196]
  We propose using k nearest neighbor representations to identify training examples responsible for a model's predictions. We show that kNN representations are effective at uncovering learned spurious associations. Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
  arXiv  Detail & Related papers  (2020-10-18T16:55:25Z)
• Understanding Neural Abstractive Summarization Models via Uncertainty [54.37665950633147]
  seq2seq abstractive summarization models generate text in a free-form manner. We study the entropy, or uncertainty, of the model's token-level predictions. We show that uncertainty is a useful perspective for analyzing summarization and text generation models more broadly.
  arXiv  Detail & Related papers  (2020-10-15T16:57:27Z)
• How does this interaction affect me? Interpretable attribution for feature interactions [19.979889568380464]
  We propose an interaction attribution and detection framework called Archipelago. Our experiments on standard annotation labels indicate our approach provides significantly more interpretable explanations than comparable methods. We also provide accompanying visualizations of our approach that give new insights into deep neural networks.
  arXiv  Detail & Related papers  (2020-06-19T05:14:24Z)
• Feature Interaction based Neural Network for Click-Through Rate Prediction [5.095988654970358]
  We propose a Feature Interaction based Neural Network (FINN) which is able to model feature interaction via a 3-dimention relation tensor. We show that our deep FINN model outperforms other state-of-the-art deep models such as PNN and DeepFM. It also indicates that our models can effectively learn the feature interactions, and achieve better performances in real-world datasets.
  arXiv  Detail & Related papers  (2020-06-07T03:53:24Z)
• Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions [55.660255727031725]
  Influence functions explain the decisions of a model by identifying influential training examples. We conduct a comparison between influence functions and common word-saliency methods on representative tasks. We develop a new measure based on influence functions that can reveal artifacts in training data.
  arXiv  Detail & Related papers  (2020-05-14T00:45:23Z)

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.