Interpretable graph learning is in need as many scientific applications depend on learning models to collect insights from graph-structured data. Previous works mostly focused on using post-hoc approaches to interpret pre-trained models (graph neural networks in particular). They argue against inherently interpretable models because the good interpretability of these models is often at the cost of their prediction accuracy. However, those post-hoc methods often fail to provide stable interpretation and may extract features that are spuriously correlated with the task. In this work, we address these issues by proposing Graph Stochastic Attention (GSAT). Derived from the information bottleneck principle, GSAT injects stochasticity to the attention weights to block the information from task-irrelevant graph components while learning stochasticity-reduced attention to select task-relevant subgraphs for interpretation. The selected subgraphs provably do not contain patterns that are spuriously correlated with the task under some assumptions. Extensive experiments on eight datasets show that GSAT outperforms the state-of-the-art methods by up to 20%$\uparrow$ in interpretation AUC and 5%$\uparrow$ in prediction accuracy. Our code is available at https://github.com/Graph-COM/GSAT.
Regression problems with time-series predictors are common in banking and many other areas of application. In this paper, we use multi-head attention networks to develop interpretable features and use them to achieve good predictive performance. The customized attention layer explicitly uses multiplicative interactions and builds feature-engineering heads that capture temporal dynamics in a parsimonious manner. Convolutional layers are used to combine multivariate time series. We also discuss methods for handling static covariates in the modeling process. Visualization and explanation tools ar…
Knowledge tracing aims to model students' past answer sequences to track the change in their knowledge acquisition during exercise activities and to predict their future learning performance. Most existing approaches ignore the fact that students' abilities are constantly changing or vary between individuals, and lack the interpretability of model predictions. To this end, in this paper, we propose a novel model based on ability attributes and attention mechanism. We first segment the interaction sequences and captures students' ability attributes, then dynamically assign students to groups wi…
Duke University（杜克大学）；InfiniaML, Inc.（InfiniaML公司）
We propose a novel and interpretable embedding method to represent the international statistical classification codes of diseases and related health problems (i.e., ICD codes). This method considers a self-attention mechanism within the disease domain and a mutual-attention mechanism jointly between diseases and procedures. This framework captures the clinical relationships between the disease codes and procedures associated with hospital admissions, and it predicts procedures according to diagnosed diseases. A self-attention network is learned to fuse the embeddings of the diseases for each a…
Queensland University of Technology（昆士兰科技大学）；IBM Research（IBM研究院）
In this paper, we address the "black-box" problem in predictive process analytics by building interpretable models that are capable to inform both what and why is a prediction. Predictive process analytics is a newly emerged discipline dedicated to providing business process intelligence in modern organisations. It uses event logs, which capture process execution traces in the form of multi-dimensional sequence data, as the key input to train predictive models. These predictive models, often built upon deep learning techniques, can be used to make predictions about the future states of busines…
Attention-based methods have played important roles in model interpretations, where the calculated attention weights are expected to highlight the critical parts of inputs~(e.g., keywords in sentences). However, recent research found that attention-as-importance interpretations often do not work as we expected. For example, learned attention weights sometimes highlight less meaningful tokens like "[SEP]", ",", and ".", and are frequently uncorrelated with other feature importance indicators like gradient-based measures. A recent debate over whether attention is an explanation or not has drawn …
Georgia Institute of Technology（佐治亚理工学院）；Sutter Health（萨特健康）
Accuracy and interpretability are two dominant features of successful predictive models. Typically, a choice must be made in favor of complex black box models such as recurrent neural networks (RNN) for accuracy versus less accurate but more interpretable traditional models such as logistic regression. This tradeoff poses challenges in medicine where both accuracy and interpretability are important. We addressed this challenge by developing the REverse Time AttentIoN model (RETAIN) for application to Electronic Health Records (EHR) data. RETAIN achieves high accuracy while remaining clinically…
University of British Columbia（不列颠哥伦比亚大学）；Tsinghua University（清华大学）
Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition. For spatial attention, we learn a saliency mask to allow the model to focus on the most salient parts of the feature maps. For temporal attention, we employ a convolutional LSTM based attention mechanism to identify the most relevant frames from an input video. Further, we propose a set of regularizers to ensure that our attention mechanism attends to c…
Stanford University（斯坦福大学）；Universidad Catolica de Chile（智利天主教大学）
A key aspect of VQA models that are interpretable is their ability to ground their answers to relevant regions in the image. Current approaches with this capability rely on supervised learning and human annotated groundings to train attention mechanisms inside the VQA architecture. Unfortunately, obtaining human annotations specific for visual grounding is difficult and expensive. In this work, we demonstrate that we can effectively train a VQA architecture with grounding supervision that can be automatically obtained from available region descriptions and object annotations. We also show that…
Disease progression models are instrumental in predicting individual-level health trajectories and understanding disease dynamics. Existing models are capable of providing either accurate predictions of patients prognoses or clinically interpretable representations of disease pathophysiology, but not both. In this paper, we develop the phased attentive state space (PASS) model of disease progression, a deep probabilistic model that captures complex representations for disease progression while maintaining clinical interpretability. Unlike Markovian state space models which assume memoryless dy…
ETH Zurich（苏黎世联邦理工学院）；EPFL Lausanne（洛桑联邦理工学院）；TalkingData Co., Ltd.（北京腾云天下科技有限公司）
In this paper, we propose an interpretable LSTM recurrent neural network, i.e., multi-variable LSTM for time series with exogenous variables. Currently, widely used attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To this end, our multi-variable LSTM equipped with tensorized hidden states is developed to learn variable specific representations, which give rise to both temporal and variable level attention. Preliminary experiments demonstrate comparable prediction performance of multi-variable L…
School of Computer Science and Engineering, UNSW Sydney, Australia（澳大利亚新南威尔士大学计算机科学与工程学院）；School of Information Technology, RMIT University, Australia（澳大利亚皇家墨尔本理工大学信息技术学院）；School of Computer Science, Northwestern Polytechnical University, China（中国西北工业大学计算机学院）；School of Software, Tsinghua University China（中国清华大学软件学院）
Multimodal features play a key role in wearable sensor-based human activity recognition (HAR). Selecting the most salient features adaptively is a promising way to maximize the effectiveness of multimodal sensor data. In this regard, we propose a "collect fully and select wisely" principle as well as an interpretable parallel recurrent model with convolutional attentions to improve the recognition performance. We first collect modality features and the relations between each pair of features to generate activity frames, and then introduce an attention mechanism to select the most prominent reg…
University of Macau（澳门大学）；Shanghai Jiaotong University（上海交通大学）
Crowd flow prediction has been increasingly investigated in intelligent urban computing field as a fundamental component of urban management system. The most challenging part of predicting crowd flow is to measure the complicated spatial-temporal dependencies. A prevalent solution employed in current methods is to divide and conquer the spatial and temporal information by various architectures (e.g., CNN/GCN, LSTM). However, this strategy has two disadvantages: (1) the sophisticated dependencies are also divided and therefore partially isolated; (2) the spatial-temporal features are transforme…
University of California, San Diego（加州大学圣迭戈分校）；Swisscom AG（瑞士电信公司）；EPFL（洛桑联邦理工学院）
We propose a method to create document representations that reflect their internal structure. We modify Tree-LSTMs to hierarchically merge basic elements such as words and sentences into blocks of increasing complexity. Our Structure Tree-LSTM implements a hierarchical attention mechanism over individual components and combinations thereof. We thus emphasize the usefulness of Tree-LSTMs for texts larger than a sentence. We show that structure-aware encoders can be used to improve the performance of document classification. We demonstrate that our method is resilient to changes to the basic bui…
Western Washington University（西华盛顿大学）；Pacific Northwest National Laboratory（太平洋西北国家实验室）
Deep learning has recently demonstrated state-of-the art performance on key tasks related to the maintenance of computer systems, such as intrusion detection, denial of service attack detection, hardware and software system failures, and malware detection. In these contexts, model interpretability is vital for administrator and analyst to trust and act on the automated analysis of machine learning models. Deep learning methods have been criticized as black box oracles which allow limited insight into decision factors. In this work we seek to "bridge the gap" between the impressive performance …
Oxford-Man Institute of Quantitative Finance, University of Oxford（牛津大学牛津-曼定量金融研究所）；Oxford Internet Institute, University of Oxford（牛津大学牛津互联网研究所）
We introduce the Momentum Transformer, an attention-based deep-learning architecture, which outperforms benchmark time-series momentum and mean-reversion trading strategies. Unlike state-of-the-art Long Short-Term Memory (LSTM) architectures, which are sequential in nature and tailored to local processing, an attention mechanism provides our architecture with a direct connection to all previous time-steps. Our architecture, an attention-LSTM hybrid, enables us to learn longer-term dependencies, improves performance when considering returns net of transaction costs and naturally adapts to new m…
MIT（麻省理工学院）；CSAIL（麻省理工学院计算机科学与人工智能实验室）；NeuroSpin（神经自旋中心）；Center for Brains, Minds, and Machines（大脑、心智与机器中心）；Department of Brain and Cognitive Sciences（脑与认知科学系）；Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）
Expert problem-solving is driven by powerful languages for thinking about problems and their solutions. Acquiring expertise means learning these languages -- systems of concepts, alongside the skills to use them. We present DreamCoder, a system that learns to solve problems by writing programs. It builds expertise by creating programming languages for expressing domain concepts, together with neural networks to guide the search for programs within these languages. A ``wake-sleep'' learning algorithm alternately extends the language with new symbolic abstractions and trains the neural network o…
University of Southern California（南加利福尼亚大学）；NAVER AI Lab（NAVER人工智能实验室）
Recently, deep reinforcement learning (DRL) methods have achieved impressive performance on tasks in a variety of domains. However, neural network policies produced with DRL methods are not human-interpretable and often have difficulty generalizing to novel scenarios. To address these issues, prior works explore learning programmatic policies that are more interpretable and structured for generalization. Yet, these works either employ limited policy representations (e.g. decision trees, state machines, or predefined program templates) or require stronger supervision (e.g. input/output state pa…
Neuro-Symbolic Operator for Interpretable and Generalizable Characterization of Complex Piezoelectric Systems
Department of Electrical Engineering, Eindhoven University of Technology（电子工程系，埃因霍温理工大学）；Department of Engineering Structures, Delft University of Technology（工程结构系，代尔夫特理工大学）；Department of Mechanical Engineering, Eindhoven University of Technology（机械工程系，埃因霍温理工大学）
University of Science and Technology of China（中国科学技术大学）；Sea AI Lab（Sea人工智能实验室）；National University of Singapore（新加坡国立大学）
In graph classification, attention and pooling-based graph neural networks (GNNs) prevail to extract the critical features from the input graph and support the prediction. They mostly follow the paradigm of learning to attend, which maximizes the mutual information between the attended graph and the ground-truth label. However, this paradigm makes GNN classifiers recklessly absorb all the statistical correlations between input features and labels in the training data, without distinguishing the causal and noncausal effects of features. Instead of underscoring the causal features, the attended …
In silico prediction of drug-target interactions (DTI) is significant for drug discovery because it can largely reduce timelines and costs in the drug development process. Specifically, deep learning-based DTI approaches have been shown promising results in terms of accuracy and low cost for the prediction. However, they pay little attention to the interpretability of their prediction results and feature-level interactions between a drug and a target. In this study, we propose a novel interpretable framework that can provide reasonable cues for the interaction sites. To this end, we elaboratel…
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
Accuracy and interpretability are two essential properties for a crime prediction model. Because of the adverse effects that the crimes can have on human life, economy and safety, we need a model that can predict future occurrence of crime as accurately as possible so that early steps can be taken to avoid the crime. On the other hand, an interpretable model reveals the reason behind a model's prediction, ensures its transparency and allows us to plan the crime prevention steps accordingly. The key challenge in developing the model is to capture the non-linear spatial dependency and temporal p…
We developed a novel, interpretable multimodal classification method to identify symptoms of mood disorders viz. depression, anxiety and anhedonia using audio, video and text collected from a smartphone application. We used CNN-based unimodal encoders to learn dynamic embeddings for each modality and then combined these through a transformer encoder. We applied these methods to a novel dataset - collected by a smartphone application - on 3002 participants across up to three recording sessions. Our method demonstrated better multimodal classification performance compared to existing methods tha…
Multi-feature concatenation and multi-classifier stacking: an interpretable and generalizable machine learning method for MDD discrimination with rsfMRI
College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）；Key Laboratory of Cognition and Personality(SWU), Ministry of Education（教育部认知与人格重点实验室（西南大学））；School of Psychology, Southwest University (SWU)（西南大学心理学部）；Southwest University Branch, Collaborative Innovation Center of Assessment Toward Basic Education Quality at Beijing Normal University（北京师范大学基础教育质量评价协同创新中心西南大学分中心）
VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention
Zhejiang University（浙江大学）；Westlake University（西湖大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Tongji University（同济大学）；ShanghaiTech University（上海科技大学）；Southern University of Science and Technology（南方科技大学）；Jilin University（吉林大学）
Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in the agent, forcing it to focus on task-relevant information by sequentially querying its view of the environment. The output of the attention mechanism allows direct observation of the information used by the agent to select its actions, enabling easier interpretation of this model than of traditional models. We analyze different strategies that the agents …
Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the vulnerability to perturbations in the mechanism, we are inspired by adversarial training (AT), which is a powerful regularization technique for enhancing the robustness of the models. In this paper, we propose a general training technique for natural language processing tasks, including AT for attention (Attention AT) and more interpretable AT for attention (Attent…
