Empowering Discovery,
Enhancing Knowledge

Concepts are an important construct in semantics, based on which humans understand the world with various levels of abstraction. With the recent advances in explainable artificial intelligence (XAI), concept-level explanations are receiving an increasing amount of attention from the broad research community. However, laypeople may find such explanations difficult to digest due to the potential knowledge gap and the concomitant cognitive load. Inspired by prior work that has explored analogies and sensemaking, we argue that augmenting concept-level explanations with analogical inference information from commonsense knowledge can be a potential solution to tackle this issue. To investigate the validity of our proposition, we first designed an effective analogy-based explanation generation method and collected 600 analogy-based explanations from 100 crowd workers. Next, we proposed a set of structured dimensions for the qualitative assessment of such explanations, and conducted an empirical evaluation of the generated analogies with experts. Our findings revealed significant positive correlations between the qualitative dimensions of analogies and the perceived helpfulness of analogy-based explanations, suggesting the effectiveness of the dimensions. To understand the practical utility and the effectiveness of analogybased explanations in assisting human decision-making, we conducted a follow-up empirical study (N= 280) on a skin cancer detection task with non-expert humans and an imperfect AI system. Thus, we designed a between-subjects study spanning five different experimental conditions with varying types of …

In this paper, we contend that the conventional approach to training and evaluating machine learning models frequently overlooks their application within the real-world organizational or societal contexts they are meant to serve. By shifting to this perspective, we redefine how we assess and choose machine learning models. Our focus is particularly on integrating these models into practical workflows that involve both machines and human experts, with human intervention occurring when machines lack sufficient confidence in their predictions. We demonstrate that traditional metrics such as accuracy and f-score fall short in capturing the true value of machine learning models in such hybrid settings. To address this issue, we introduce a simple but theoretically sound strategy to adapt existing machine learning models so as to maximize value. An extensive experimental evaluation highlights the importance of the value-based perspective in evaluating models, and the impact of calibration and out-of-distribution settings on model value.

深度学习在滚动轴承故障诊断中具有广泛的应用, 然而, 现实中的监测数据往往具有不平衡性, 这就会对模型的诊断性能产生很大影响. 因此, 提出一种基于改进门控卷积神经网络 (Improved Gated Convolutional Neural Network, IGCNN) 的故障诊断方法, 用于数据不平衡条件下的故障诊断. 首先, 提出改进门控卷积层以增强特征提取能力, 通过批量归一化技术提高模型的泛化能力. 然后, 使用标签分布感知边界 (Label-distribution-aware Margin, LDAM) 损失函数提高模型对少数类的敏感度, 减小数据不平衡对模型的影响. 将所提算法应用在两组故障轴承数据上, 在数据不平衡率为 20: 1 的情况下, 所提算法仍然可达到 92.71% 和 94.47% 的故障识别率, 而对比的其他主流深度学习模型在该情况下只有 60%~ 72% 的准确率, 表明所提方法在数据集严重不平衡情况下具有很强的诊断能力和鲁棒性.

We construct the generalized and (q, t)-deformed partition functions through W representations, where the expansions are respectively with respect to the generalized Jack and Macdonald polynomials labeled by N-tuple of Young diagrams. We find that there are the profound interrelations between our deformed partition functions and the 4d and 5d Nekrasov partition functions. Since the corresponding Nekrasov partition functions can be given by vertex operators, the remarkable connection between our and (q, t)-deformed W-operators and vertex operators is revealed in this paper. In addition, we investigate the higher Hamiltonians for the generalized Jack and Macdonald polynomials.