CFChun Fan

Chun Fan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chun Fan has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    DORIS: Personalized course recommendation system based on deep learning

    by Yinping Ma, Rongbin Ouyang, Xinzheng Long, Zhitong Gao, Tianping Lai, Chun Fan

    Course recommendation aims at finding proper and attractive courses from massive candidates for students based on their needs, and it plays a significant role in the curricula-variable system. However, nearly all students nowadays need help selecting appropriate courses from abundant ones. The emergence and application of personalized course recommendations can release students from that cognitive overload problem. However, it still needs to mature and improve its scalability, sparsity, and cold start problems resulting in poor quality recommendations. Therefore, this paper proposes a novel personalized course recommendation system based on deep factorization machine (DeepFM), namelyDeep PersOnalized couRse RecommendatIonSystem (DORIS), which selects the most appropriate courses for students according to their basic information, interests and the details of all courses. The experimental results illustrate that our proposed method outperforms other approaches.


  • Critique of “A Parallel Framework for Constraint-Based Bayesian Network Learning via Markov Blanket Discovery” by SCC Team From Peking University

    by Jiaqi Si, Junyi Guo, Zhewen Hao, Wenyang He, Ruihan Li, Yueyang Pan, Zhenxin Fu, Chun Fan

    Ankit Srivastava et al. [1] proposed a parallel framework for Constraint-Based Bayesian Network (BN) Learning via Markov Blanket Discovery (referred to as ramBLe) and implemented it over three existing BN learning algorithms, namely, GS, IAMB and Inter-IAMB. As part of the Student Cluster Competition at SC21, we reproduce the computational efficiency of ramBLe on our assigned Oracle cluster. The cluster has 4x36 cores in total with 100 Gbps RoCE v2 support and is equipped with Centos-compatible Oracle Linux. Our experiments, covering the same three algorithms of ramBLe, evaluate its strong and weak scalability of the algorithms using real COVID-19 data sets. We verify part of the conclusions in the paper and propose our explanation of the differences.


  • Open Access

    Sentence Similarity Based on Contexts

    by Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan

    Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; and (2) there is a training-test gap for unsupervised language modeling (LM) based models to compute semantic scores between sentences, since sentence-level semantics are not explicitly modeled at training. This results in inferior performances in this task. In this work, we propose a new framework to address these two issues. The proposed framework is based on the core idea that the meaning of a sentence should be defined by its contexts, and that sentence similarity can be measured by comparing the probabilities of generating two sentences given the same context. The proposed framework is able to generate high-quality, large-scale dataset with semantic similarity scores between two sentences in an unsupervised manner, with which the train-test gap can be largely bridged. Extensive experiments show that the proposed framework achieves significant performance boosts over existing baselines under both the supervised and unsupervised settings across different datasets.


  • Open Access

    Sentence Similarity Based on Contexts

    by Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan

    Existing methods to measure sentence similarity are faced with two challenges: (1) labeled datasets are usually limited in size, making them insufficient to train supervised neural models; (2) there is a training-test gap for unsupervised language modeling (LM) based models to compute semantic scores between sentences, since sentence-level semantics are not explicitly modeled at training. This results in inferior performances in this task. In this work, we propose a new framework to address these two issues. The proposed framework is based on the core idea that the meaning of a sentence should be defined by its contexts, and that sentence similarity can be measured by comparing the probabilities of generating two sentences given the same context. The proposed framework is able to generate high-quality, large-scale dataset with semantic similarity scores between two sentences in an unsupervised manner, with which the train-test gap can be largely bridged. Extensive experiments show that the proposed framework achieves significant performance boosts over existing baselines under both the supervised and unsupervised settings across different datasets.


  • Open Access

    Self-Explaining Structures Improve NLP Models

    by Zijun Sun, Chun Fan, Qinghong Han, Xiaofei Sun, Yuxian Meng, Fei Wu, Jiwei Li

    Existing approaches to explaining deep learning models in NLP usually suffer from two major drawbacks: (1) the main model and the explaining model are decoupled: an additional probing or surrogate model is used to interpret an existing model, and thus existing explaining tools are not self-explainable; (2) the probing model is only able to explain a model's predictions by operating on low-level features by computing saliency scores for individual words but are clumsy at high-level text units such as phrases, sentences, or paragraphs. To deal with these two issues, in this paper, we propose a simple yet general and effective self-explaining framework for deep learning models in NLP. The key point of the proposed framework is to put an additional layer, as is called by the interpretation layer, on top of any existing NLP model. This layer aggregates the information for each text span, which is then associated with a specific weight, and their weighted combination is fed to the softmax function for the final prediction. The proposed model comes with the following merits: (1) span weights make the model self-explainable and do not require an additional probing model for interpretation; (2) the proposed model is general and can be adapted to any existing deep learning structures in NLP; (3) the weight associated with each text span provides direct importance scores for higher-level text units such as phrases and sentences. We for the first time show that interpretability does not come at the cost of performance: a neural model of self-explaining features obtains better performances than its counterpart without the self-explaining nature, achieving a new SOTA performance of 59.1 on SST-5 and a new SOTA performance of 92.3 on SNLI.


  • Open Access

    Neural Semi-supervised Learning for Text Classification Under Large-Scale Pretraining

    by Zijun Sun, Chun Fan, Xiaofei Sun, Yuxian Meng, Fei Wu, Jiwei Li

    The goal of semi-supervised learning is to utilize the unlabeled, in-domain dataset U to improve models trained on the labeled dataset D. Under the context of large-scale language-model (LM) pretraining, how we can make the best use of U is poorly understood: is semi-supervised learning still beneficial with the presence of large-scale pretraining? should U be used for in-domain LM pretraining or pseudo-label generation? how should the pseudo-label based semi-supervised model be actually implemented? how different semi-supervised strategies affect performances regarding D of different sizes, U of different sizes, etc. In this paper, we conduct comprehensive studies on semi-supervised learning in the task of text classification under the context of large-scale LM pretraining. Our studies shed important lights on the behavior of semi-supervised learning methods: (1) with the presence of in-domain pretraining LM on U, open-domain LM pretraining is unnecessary; (2) both the in-domain pretraining strategy and the pseudo-label based strategy introduce significant performance boosts, with the former performing better with larger U, the latter performing better with smaller U, and the combination leading to the largest performance boost; (3) self-training (pretraining first on pseudo labels D' and then fine-tuning on D) yields better performances when D is small, while joint training on the combination of pseudo labels D' and the original dataset D yields better performances when D is large. Using semi-supervised learning strategies, we are able to achieve a performance of around 93.8% accuracy with only 50 training data points on the IMDB dataset, and a competitive performance of 96.6% with the full IMDB dataset. Our work marks an initial step in understanding the behavior of semi-supervised learning models under the context of large-scale pretraining.

  • Open Access

    Pair the Dots: Jointly Examining Training History and Test Stimuli for Model Interpretability

    by Yuxian Meng, Chun Fan, Zijun Sun, Eduard Hovy, Fei Wu, Jiwei Li

    Any prediction from a model is made by a combination of learning history and test stimuli. This provides significant insights for improving model interpretability: {\it because of which part(s) of which training example(s), the model attends to which part(s) of a test example}. Unfortunately, existing methods to interpret a model's predictions are only able to capture a single aspect of either test stimuli or learning history, and evidences from both are never combined or integrated. In this paper, we propose an efficient and differentiable approach to make it feasible to interpret a model's prediction by jointly examining training history and test stimuli. Test stimuli is first identified by gradient-based methods, signifying {\it the part of a test example that the model attends to}. The gradient-based saliency scores are then propagated to training examples using influence functions to identify {\it which part(s) of which training example(s)} make the model attends to the test stimuli. The system is differentiable and time efficient: the adoption of saliency scores from gradient-based methods allows us to efficiently trace a model's prediction through test stimuli, and then back to training examples through influence functions. We demonstrate that the proposed methodology offers clear explanations about neural model decisions, along with being useful for performing error analysis, crafting adversarial examples and fixing erroneously classified examples.