Yuqi Yi

Yuqi Yi

Auto-generated profile, based on publicly available information

Yuqi Yi

Department of Computer Science and Engineering, MoE Key Laboratory of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 April 2021 in IEEE Access
Verified
Journal Article
Open access
HLHaoran Luo
Haoran Luo
Fan ChengFan Cheng
Fan Cheng
HYHeng Yu
Heng Yu
YYYuqi Yi
Yuqi Yi
Deep neural networks have been proved a success in multiple fields. However, researchers still favor traditional approaches to obtain more interpretable models, such as Bayesian methods and decision trees when processing heterogeneous tabular data. Such models are hard to differentiate, thus inconvenient to be integrated into end-to-end settings. On the other hand, traditional neural networks are differentiable but perform poorly on tabular data. We propose a hierarchical differentiable neural regression model, Soft Decision Tree Regressor (SDTR). SDTR imitates a binary decision tree by a differentiable neural network and is plausible for ensemble schemes like bagging and boosting. The SDTR method was evaluated on multiple tabular-based regression tasks (YearPredictionMSD, MSLR-Web10K, Yahoo LETOR, SARCOS and Wine quality). Its performance is comparable with non-differentiable models (gradient boosting decision trees) and better than uninterpretable models (regular FCNN). On top of that, it can produce fair results with a restricted number of parameters, only using a small forest or even a single tree. We also propose an “average entropy” metric to evaluate the level of interpretability of a trained, soft decision tree neural network. This metric also helps to select proper structure and hyperparameters for such networks.

12 February 2021 in IEEE Access
Verified
Journal Article
Open access
YYYuqi Yi
Yuqi Yi
LJLuhua Jin
Luhua Jin
HYHeng Yu
Heng Yu
HLHaoran Luo
Haoran Luo
Fan ChengFan Cheng
Fan Cheng
Given a network, local community detection aims at finding the community that contains a set of query nodes (seed nodes). Random walk (RW) based algorithms have shown great success in various local community detection scenarios. Starting from the seed nodes, RW based algorithms continuously sample random walk paths to get the clustering result. However, current RW based algorithms for local clustering are faced with the following two problems. The random walker is insensitive to the community boundary and might have an unbalanced walk. These problems would have a negative effect on the clustering result of RW based algorithms. In this paper, we propose a density sensitive random walk algorithms (DSRW) for local community detection. By integrating the graph density information into the random walk process, the problems are resolved and the clustering result is improved. We provide the convergence proof of DSRW algorithm and perform extensive experiments on both real and synthetic datasets. Results show that our DSRW algorithm has achieved the state-of-the-art result in most scenarios.

27 January 2021 in IEEE Access
Verified
Journal Article
Open access
HYHeng Yu
Heng Yu
HLHaoran Luo
Haoran Luo
YYYuqi Yi
Yuqi Yi
Fan ChengFan Cheng
Fan Cheng
Unsupervised neural machine translation (UNMT) has recently achieved significant progress without requirement on any parallel data. The models for UNMT are typically the sequence-to-sequence architecture with an encoder to map sentences in different languages to a shared latent space, and a decoder to generate their corresponding translation. Denoising autoencoding and back-translation are called in every iteration for the models to learn the relationship of sentence pairs in languages or between languages. However, sentences generated by the noise model of autoencoding or the reverse model of back-translation are normally different from those written by humans, which may cause inference bias. In this paper, we propose a regularization method for back-translation to explicitly draw representations of sentence pairs closer in the shared space. To enhance the robustness to sentences after autoencoding or back-translation, the adversarial attack on representations is applied. Experiments on unsupervised English $\leftrightarrow $ French, English $\leftrightarrow $ German and English $\leftrightarrow $ Romanian benchmarks show that our approach outperforms the cross-lingual language model (XLM) baseline by $0.4\sim 1.8$ BLEU scores. Additionally, the boost on noisy test sets in most translation directions is over 5 BLEU scores.