For the interpretability of deep neural networks (DNNs) in visual-related tasks, existing explanation methods commonly generate a saliency map based on the linear relation between output results and input features. However, when the explanation conflicts with a human visual examination, these methods do not provide further evidence to analyze the saliency explanation. Most may fail to provide feature attribution with identifiable semantics or produce misleading explanations due to their insufficient robustness. In this paper, we first propose four key characteristics (richness, adaptivity, exclusiveness, and fairness) to evaluate the existing linear relation-based explanation method, and then construct an interpretable linear model to satisfy them. We formalize the characteristics and develop a novel explanation method based on this. We extract and reconstruct key exclusive semantic features from the feature map using the Nonnegative Matrix Factorization (NMF) algorithm, utilize the information entropy model to determine the number of features adaptively and their richness, and then linearly combine each feature with fairly assigned weights using an approximate Shapley algorithm to generate the saliency map. Compared with the state-of-the-art methods, our explanations of different datasets and DNNs are more convincing and robust in terms of Average drop (AD), Average increase (AI), Deletions (Del), and Insertions (Ins). Our supplementary experiments provide sufficient evidence that the four characteristics guarantee the feasibility of feature attribution analysis and enhance the quality of the resulting explanations.

Few-shot sequence labeling aims to identify novel classes based on only a few labeled samples. Existing methods solve the data scarcity problem mainly by designing token-level or span-level labeling models based on metric learning. However, these methods are only trained at a single granularity (i.e., either token-level or span-level) and have some weaknesses of the corresponding granularity. In this article, we first unify token- and span-level supervisions and propose a Consistent Dual Adaptive Prototypical (CDAP) network for few-shot sequence labeling. CDAP contains the token- and span-level networks, jointly trained at different granularities. To align the outputs of two networks, we further propose a consistent loss to enable them to learn from each other. During the inference phase, we propose a consistent greedy inference algorithm that first adjusts the predicted probability and then greedily selects non-overlapping spans with maximum probability. Extensive experiments show that our model achieves new state-of-the-art results on three benchmark datasets. All the code and data of this work will be released at https://github.com/zifengcheng/CDAP .

Cognitive diagnosis is a fundamental issue of intelligent education platforms, whose goal is to reveal the mastery of students on knowledge concepts. Recently, certain efforts have been made to improve the diagnosis precision, by designing deep neural networks-based diagnostic functions or incorporating more rich context features to enhance the representation of students and exercises. However, how to interpretably infer the student's mastery over non-interactive knowledge concepts (i.e., knowledge concepts not related to his/her exercising records) still remains challenging, especially when not giving relations between knowledge concepts. To this end, we propose a Knowledge-Sensed Cognitive Diagnosis (KSCD) framework, aiming at learning intrinsic relations among knowledge concepts from student response logs and incorporating them for inferring students' mastery over all knowledge concepts in an end-to-end manner. Specifically, we firstly project students, exercises and knowledge concepts into embedding representation matrices, where the intrinsic relations among knowledge concepts are reflected in the knowledge embedding representation matrix. Then, the knowledge-sensed student knowledge mastery vector and exercise factor vectors are obtained by the multiply product of their embedding representations and the knowledge embedding representation matrix, which make the student's mastery of non-interactive knowledge concepts be interpretably inferred. Finally, we can utilize classical student-exercise interaction functions to predict student's exercising performance and jointly train the model. In additional, we also design a new function to better model the student-exercise interactions. Extensive experimental results on two real-world datasets clearly show the significant performance gain of our KSCD framework, especially in predicting students' mastery over non-interactive knowledge concepts, by comparing to state-of-the-art cognitive diagnosis models (CDMs).

With the rapid development of intelligent education platforms, how to enhance the performance of diagnosing students' knowledge proficiency has become an important issue, e.g., by incorporating the prerequisite relation of knowledge concepts. Unfortunately, the differentiated influence from different predecessor concepts to successor concepts is still underexplored in existing approaches. To this end, we propose a Prerequisite Attention model for Knowledge Proficiency diagnosis of students (PAKP) to learn the attentive weights of precursor concepts on successor concepts and model it for inferring the knowledge proficiency. Specifically, given the student response records and knowledge prerequisite graph, we design an embedding layer to output the representations of students, exercises, and concepts. Influence coefficient among concepts is calculated via an efficient attention mechanism in a fusion layer. Finally, the performance of each student is predicted based on the mined student and exercise factors. Extensive experiments on real-data sets demonstrate that PAKP exhibits great efficiency and interpretability advantages without accuracy loss.

Latent Dirichlet allocation (LDA) is a popular topic modeling technique in academia but less so in industry, especially in large-scale applications involving search engine and online advertising systems. A main underlying reason is that the topic models used have been too small in scale to be useful; for example, some of the largest LDA models reported in literature have up to 10 3 topics, which difficultly cover the long-tail semantic word sets. In this article, we show that the number of topics is a key factor that can significantly boost the utility of topic-modeling systems. In particular, we show that a “big” LDA model with at least 10 5 topics inferred from 10 9 search queries can achieve a significant improvement on industrial search engine and online advertising systems, both of which serve hundreds of millions of users. We develop a novel distributed system called Peacock to learn big LDA models from big data. The main features of Peacock include hierarchical distributed architecture, real-time prediction, and topic de-duplication. We empirically demonstrate that the Peacock system is capable of providing significant benefits via highly scalable LDA topic models for several industrial applications.

Video-based target tracking is a challenging task, because there always appears to be complex occlusion among the varying number of objects. Also, in practice, it is very common that the objects in a scene move irregularly with abrupt turns, which results in an interesting heavy-tailed phenomenon. As simulation has to run exceptionally long enough to capture the effect of the distribution tail, it is arduous to simulate heavy-tailed distribution. In this paper, we propose a new view to target tracking from a heavy-tailed perspective, establishing a simple but novel Multivariate Laplace Filter (MLF) tracking model, which efficiently and accurately describes the heavy-tailed issue and dramatically surmounts it. Some experimental results show the good performance of the proposed method.