SelfMatch: Robust semisupervised time‐series classification with self‐distillation

Xing, Huanlai; Xiao, Zhiwen; Zhan, Dawei; Luo, Shouxi; Dai, Penglin; Li, Ké

doi:10.1002/int.22957

Cited by 97 publications

(16 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ABCN2 was used in an intelligent tutoring system (Woolf, 2010) to teach students arguing strategies (Guid et al, 2019). The intelligent system by Xing et al (2022b) uses feature extraction in semi-supervised learning and self-distillation; a similar feature extractor was used in the federated distillation learning system (Xing et al, 2022a). The last two methods are specific to time-series classification and do not use explicit constructive operators.…”

Section: Standalone Feature Constructionmentioning

confidence: 99%

Feature construction using explanations of individual predictions

Vouk,

Guid,

Robnik-Šikonja

2023

Preprint

View full text Add to dashboard Cite

Feature construction can contribute to comprehensibility and performance of machine learning models. Unfortunately, it usually requires exhaustive search in the attribute space or time-consuming human involvement to generate meaningful features. We propose a novel heuristic approach for reducing the search space based on aggregation of instance-based explanations of predictive models. The proposed Explainable Feature Construction (EFC) methodology identifies groups of cooccurring attributes exposed by popular explanation methods, such as IME and SHAP. We empirically show that reducing the search to these groups significantly reduces the time of feature construction using logical, relational, Cartesian, numerical, and threshold (num-of-N and X-of-N) constructive operators. An analysis on 10 transparent synthetic datasets shows that EFC effectively identifies informative groups of attributes and constructs relevant features. Using 30 real-world classification datasets, we show significant improvements in classification accuracy for several classifiers and demonstrate the feasibility of the proposed feature construction even for large datasets. Finally, EFC generated interpretable features on a real-world problem from the financial industry, which were confirmed by a domain expert.

show abstract

Section: Standalone Feature Constructionmentioning

confidence: 99%

Feature construction using explanations of individual predictions

Vouk,

Guid,

Robnik-Šikonja

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…improved. For example, in [28], a deep-learning feature extractor for time-series data is designed for relation extraction, and the clustering effect achieved significant improvement. Nonetheless, in view of the unknown data distribution in actual problems, it is difficult to determine which clustering algorithm can get better clustering results.…”

Section: U N C O R R E C T E D a U T H O R P R O O Fmentioning

confidence: 99%

Fuzzy-Rough induced spectral ensemble clustering

Yue

Deng

et al. 2023

IFS

View full text Add to dashboard Cite

Ensemble clustering helps achieve fast clustering under abundant computing resources by constructing multiple base clusterings. Compared with the standard single clustering algorithm, ensemble clustering integrates the advantages of multiple clustering algorithms and has stronger robustness and applicability. Nevertheless, most ensemble clustering algorithms treat each base clustering result equally and ignore the difference of clusters. If a cluster in a base clustering is reliable/unreliable, it should play a critical/uncritical role in the ensemble process. Fuzzy-rough sets offer a high degree of flexibility in enabling the vagueness and imprecision present in real-valued data. In this paper, a novel fuzzy-rough induced spectral ensemble approach is proposed to improve the performance of clustering. Specifically, the significance of clusters is differentiated, and the unacceptable degree and reliability of clusters formed in base clustering are induced based on fuzzy-rough lower approximation. Based on defined cluster reliability, a new co-association matrix is generated to enhance the effect of diverse base clusterings. Finally, a novel consensus spectral function is defined by the constructed adjacency matrix, which can lead to significantly better results. Experimental results confirm that the proposed approach works effectively and outperforms many state-of-the-art ensemble clustering algorithms and base clustering, which illustrates the superiority of the novel algorithm.

show abstract

“…Moreover, to alleviate the issue of high dimension and sparsity of tag information in actual scenarios, the author in [24] developed two novel heterogeneous knowledge distillation methods in featurelevel and label-level to build relations between User-oriented autoencoder and item-oriented autoencoder. In the recent literature, several works proposing self-distillation [25,26] have also been emerged. The work in [27] introduced a weighting mechanism to dynamically put less weights on uncertain samples and showed promising results.…”

Section: Recommender Systemmentioning

confidence: 99%

Fully adaptive recommendation paradigm: top-enhanced recommender distillation for intelligent education systems

Ren

Liang

Shang

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Top-N recommendation has received great attention in assisting students in providing personalized learning guidance on the required subject/domain. Generally, existing approaches mainly aim to maximize the overall accuracy of the recommendation list while ignoring the accuracy of highly ranked recommended exercises, which seriously affects the students’ learning enthusiasm. Motivated by the Knowledge Distillation (KD) technique, we skillfully design a fully adaptive recommendation paradigm named Top-enhanced Recommender Distillation framework (TERD) to improve the recommendation effect of the top positions. Specifically, the proposed TERD transfers the knowledge of an arbitrary recommender (teacher network), and injects it into a well-designed student network. The prior knowledge provided by the teacher network, including student-exercise embeddings, and candidate exercise subsets, are further utilized to define the state and action space of the student network (i.e., DDQN). In addition, the student network introduces a well-designed state representation scheme and an effective individual ability tracing model to enhance the recommendation accuracy of top positions. The developed TERD follows a flexible model-agnostic paradigm that not only simplifies the action space of the student network, but also promotes the recommendation accuracy of the top position, thus enhancing the students’ motivation and engagement in e-learning environment. We implement our proposed approach on three well-established datasets and evaluate its Top-enhanced performance. The experimental evaluation on three publicly available datasets shows that our proposed TERD scheme effectively resolves the Top-enhanced recommendation issue.

show abstract

SelfMatch: Robust semisupervised time‐series classification with self‐distillation

Cited by 97 publications

References 52 publications

Feature construction using explanations of individual predictions

Feature construction using explanations of individual predictions

Fuzzy-Rough induced spectral ensemble clustering

Fully adaptive recommendation paradigm: top-enhanced recommender distillation for intelligent education systems

Contact Info

Product

Resources

About