Sen Yang

Zhishan Zhao, Sen Yang, Guohui Liu et al.

As a critical component for online advertising and marking, click-through rate (CTR) prediction has draw lots of attentions from both industry and academia field. Recently, the deep learning has become the mainstream methodological choice for CTR. Despite of sustainable efforts have been made, existing approaches still pose several challenges. On the one hand, high-order interaction between the features is under-explored. On the other hand, high-order interactions may neglect the semantic information from the low-order fields. In this paper, we proposed a novel prediction method, named FINT, that employs the Field-aware INTeraction layer which captures high-order feature interactions while retaining the low-order field information. To empirically investigate the effectiveness and robustness of the FINT, we perform extensive experiments on the three realistic databases: KDD2012, Criteo and Avazu. The obtained results demonstrate that the FINT can significantly improve the performance compared to the existing methods, without increasing the amount of computation required. Moreover, the proposed method brought about 2.72\% increase to the advertising revenue of a big online video app through A/B testing. To better promote the research in CTR field, we released our code as well as reference implementation at: https://github.com/zhishan01/FINT.

Sen Yang, Zhibin Quan, Mu Nie et al.

While CNN-based models have made remarkable progress on human pose estimation, what spatial dependencies they capture to localize keypoints remains unclear. In this work, we propose a model called \textbf{TransPose}, which introduces Transformer for human pose estimation. The attention layers built in Transformer enable our model to capture long-range relationships efficiently and also can reveal what dependencies the predicted keypoints rely on. To predict keypoint heatmaps, the last attention layer acts as an aggregator, which collects contributions from image clues and forms maximum positions of keypoints. Such a heatmap-based localization approach via Transformer conforms to the principle of Activation Maximization~\cite{erhan2009visualizing}. And the revealed dependencies are image-specific and fine-grained, which also can provide evidence of how the model handles special cases, e.g., occlusion. The experiments show that TransPose achieves 75.8 AP and 75.0 AP on COCO validation and test-dev sets, while being more lightweight and faster than mainstream CNN architectures. The TransPose model also transfers very well on MPII benchmark, achieving superior performance on the test set when fine-tuned with small training costs. Code and pre-trained models are publicly available\footnote{\url{https://github.com/yangsenius/TransPose}}.

Sen Yang, Wankou Yang, Zhen Cui

Neural Architecture Search (NAS) technologies have emerged in many domains to jointly learn the architectures and weights of the neural network. However, most existing NAS works claim they are task-specific and focus only on optimizing a single architecture to replace a human-designed neural network, in fact, their search processes are almost independent of domain knowledge of the tasks. In this paper, we propose Pose Neural Fabrics Search (PoseNFS). We explore a new solution for NAS and human pose estimation task: part-specific neural architecture search, which can be seen as a variant of multi-task learning. Firstly, we design a new neural architecture search space, Cell-based Neural Fabric (CNF), to learn micro as well as macro neural architecture using a differentiable search strategy. Then, we view locating human keypoints as multiple disentangled prediction sub-tasks, and then use prior knowledge of body structure as guidance to search for multiple part-specific neural architectures for different human parts. After search, all these part-specific CNFs have distinct micro and macro architecture parameters. The results show that such knowledge-guided NAS-based architectures have obvious performance improvements to a hand-designed part-based baseline model. The experiments on MPII and MS-COCO datasets demonstrate that PoseNFS\footnote{Code is available at \url{https://github.com/yangsenius/PoseNFS}} can achieve comparable performance to some efficient and state-of-the-art methods.

Wenjin Zhang, Keyi Li, Sen Yang et al.

Conventional methods in semi-supervised learning (SSL) often face challenges related to limited data utilization, mainly due to their reliance on threshold-based techniques for selecting high-confidence unlabeled data during training. Various efforts (e.g., FreeMatch) have been made to enhance data utilization by tweaking the thresholds, yet none have managed to use 100% of the available data. To overcome this limitation and improve SSL performance, we introduce \algo, a novel algorithm that fully utilizes unlabeled data to boost semi-supervised learning. \algo integrates a self-supervised learning strategy, i.e., Masked Autoencoder (MAE), that uses all available data to enforce the visual representation learning. This enables the SSL algorithm to leverage all available data, including samples typically filtered out by traditional methods. In addition, we propose a synthetic data training approach to further increase data utilization and improve generalization. These innovations lead \algo to achieve state-of-the-art results on challenging datasets. For instance, on CIFAR-100 with 2 labels per class, STL-10 with 4 labels per class, and Euro-SAT with 2 labels per class, \algo achieves low error rates of 18.71%, 9.47%, and 3.07%, respectively. The code will be made publicly available.

Yuejiao Fei, Leyang Cui, Sen Yang et al.

Grammatical error correction systems improve written communication by detecting and correcting language mistakes. To help language learners better understand why the GEC system makes a certain correction, the causes of errors (evidence words) and the corresponding error types are two key factors. To enhance GEC systems with explanations, we introduce EXPECT, a large dataset annotated with evidence words and grammatical error types. We propose several baselines and analysis to understand this task. Furthermore, human evaluation verifies our explainable GEC system's explanations can assist second-language learners in determining whether to accept a correction suggestion and in understanding the associated grammar rule.

Sen Yang, Zhicheng Wang, Ze Chen et al.

This paper presents a new method to solve keypoint detection and instance association by using Transformer. For bottom-up multi-person pose estimation models, they need to detect keypoints and learn associative information between keypoints. We argue that these problems can be entirely solved by Transformer. Specifically, the self-attention in Transformer measures dependencies between any pair of locations, which can provide association information for keypoints grouping. However, the naive attention patterns are still not subjectively controlled, so there is no guarantee that the keypoints will always attend to the instances to which they belong. To address it we propose a novel approach of supervising self-attention for multi-person keypoint detection and instance association. By using instance masks to supervise self-attention to be instance-aware, we can assign the detected keypoints to their corresponding instances based on the pairwise attention scores, without using pre-defined offset vector fields or embedding like CNN-based bottom-up models. An additional benefit of our method is that the instance segmentation results of any number of people can be directly obtained from the supervised attention matrix, thereby simplifying the pixel assignment pipeline. The experiments on the COCO multi-person keypoint detection challenge and person instance segmentation task demonstrate the effectiveness and simplicity of the proposed method and show a promising way to control self-attention behavior for specific purposes.

Yu Shen, Yang Li, Jian Zheng et al.

Designing neural architectures requires immense manual efforts. This has promoted the development of neural architecture search (NAS) to automate the design. While previous NAS methods achieve promising results but run slowly, zero-cost proxies run extremely fast but are less promising. Therefore, it is of great potential to accelerate NAS via those zero-cost proxies. The existing method has two limitations, which are unforeseeable reliability and one-shot usage. To address the limitations, we present ProxyBO, an efficient Bayesian optimization (BO) framework that utilizes the zero-cost proxies to accelerate neural architecture search. We apply the generalization ability measurement to estimate the fitness of proxies on the task during each iteration and design a novel acquisition function to combine BO with zero-cost proxies based on their dynamic influence. Extensive empirical studies show that ProxyBO consistently outperforms competitive baselines on five tasks from three public benchmarks. Concretely, ProxyBO achieves up to 5.41x and 3.86x speedups over the state-of-the-art approaches REA and BRP-NAS.

Yi Guo, Huan Yuan, Jianchao Tan et al.

Model compression techniques are recently gaining explosive attention for obtaining efficient AI models for various real-time applications. Channel pruning is one important compression strategy and is widely used in slimming various DNNs. Previous gate-based or importance-based pruning methods aim to remove channels whose importance is smallest. However, it remains unclear what criteria the channel importance should be measured on, leading to various channel selection heuristics. Some other sampling-based pruning methods deploy sampling strategies to train sub-nets, which often causes the training instability and the compressed model's degraded performance. In view of the research gaps, we present a new module named Gates with Differentiable Polarization (GDP), inspired by principled optimization ideas. GDP can be plugged before convolutional layers without bells and whistles, to control the on-and-off of each channel or whole layer block. During the training process, the polarization effect will drive a subset of gates to smoothly decrease to exact zero, while other gates gradually stay away from zero by a large margin. When training terminates, those zero-gated channels can be painlessly removed, while other non-zero gates can be absorbed into the succeeding convolution kernel, causing completely no interruption to training nor damage to the trained model. Experiments conducted over CIFAR-10 and ImageNet datasets show that the proposed GDP algorithm achieves the state-of-the-art performance on various benchmark DNNs at a broad range of pruning ratios. We also apply GDP to DeepLabV3Plus-ResNet50 on the challenging Pascal VOC segmentation task, whose test performance sees no drop (even slightly improved) with over 60% FLOPs saving.

Xuefan Zha, Wentao Zhu, Tingxun Lv et al.

Spatio-temporal representational learning has been widely adopted in various fields such as action recognition, video object segmentation, and action anticipation. Previous spatio-temporal representational learning approaches primarily employ ConvNets or sequential models,e.g., LSTM, to learn the intra-frame and inter-frame features. Recently, Transformer models have successfully dominated the study of natural language processing (NLP), image classification, etc. However, the pure-Transformer based spatio-temporal learning can be prohibitively costly on memory and computation to extract fine-grained features from a tiny patch. To tackle the training difficulty and enhance the spatio-temporal learning, we construct a shifted chunk Transformer with pure self-attention blocks. Leveraging the recent efficient Transformer design in NLP, this shifted chunk Transformer can learn hierarchical spatio-temporal features from a local tiny patch to a global video clip. Our shifted self-attention can also effectively model complicated inter-frame variances. Furthermore, we build a clip encoder based on Transformer to model long-term temporal dependencies. We conduct thorough ablation studies to validate each component and hyper-parameters in our shifted chunk Transformer, and it outperforms previous state-of-the-art approaches on Kinetics-400, Kinetics-600, UCF101, and HMDB51.

Shangfeng Dai, Haobin Lin, Zhichen Zhao et al.

Recommendation for new users, also called user cold start, has been a well-recognized challenge for online recommender systems. Most existing methods view the crux as the lack of initial data. However, in this paper, we argue that there are neglected problems: 1) New users' behaviour follows much different distributions from regular users. 2) Although personalized features are involved, heavily imbalanced samples prevent the model from balancing new/regular user distributions, as if the personalized features are overwhelmed. We name the problem as the "submergence" of personalization. To tackle this problem, we propose a novel module: Personalized COld Start MOdules (POSO). Considering from a model architecture perspective, POSO personalizes existing modules by introducing multiple user-group-specialized sub-modules. Then, it fuses their outputs by personalized gates, resulting in comprehensive representations. In such way, POSO projects imbalanced features to even modules. POSO can be flexibly integrated into many existing modules and effectively improves their performance with negligible computational overheads. The proposed method shows remarkable advantage in industrial scenario. It has been deployed on the large-scale recommender system of Kwai, and improves new user Watch Time by a large margin (+7.75%). Moreover, POSO can be further generalized to regular users, inactive users and returning users (+2%-3% on Watch Time), as well as item cold start (+3.8% on Watch Time). Its effectiveness has also been verified on public dataset (MovieLens 20M). We believe such practical experience can be well generalized to other scenarios.

Shaoduo Gan, Xiangru Lian, Rui Wang et al.

Recent years have witnessed a growing list of systems for distributed data-parallel training. Existing systems largely fit into two paradigms, i.e., parameter server and MPI-style collective operations. On the algorithmic side, researchers have proposed a wide range of techniques to lower the communication via system relaxations: quantization, decentralization, and communication delay. However, most, if not all, existing systems only rely on standard synchronous and asynchronous stochastic gradient (SG) based optimization, therefore, cannot take advantage of all possible optimizations that the machine learning community has been developing recently. Given this emerging gap between the current landscapes of systems and theory, we build BAGUA, a MPI-style communication library, providing a collection of primitives, that is both flexible and modular to support state-of-the-art system relaxation techniques of distributed training. Powered by this design, BAGUA has a great ability to implement and extend various state-of-the-art distributed learning algorithms. In a production cluster with up to 16 machines (128 GPUs), BAGUA can outperform PyTorch-DDP, Horovod and BytePS in the end-to-end training time by a significant margin (up to 2 times) across a diverse range of tasks. Moreover, we conduct a rigorous tradeoff exploration showing that different algorithms and system relaxations achieve the best performance over different network conditions.

Yanjie Li, Shoukui Zhang, Zhicheng Wang et al.

Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the constraint relationships between keypoints. In this paper, we propose a novel approach based on Token representation for human Pose estimation~(TokenPose). In detail, each keypoint is explicitly embedded as a token to simultaneously learn constraint relationships and appearance cues from images. Extensive experiments show that the small and large TokenPose models are on par with state-of-the-art CNN-based counterparts while being more lightweight. Specifically, our TokenPose-S and TokenPose-L achieve $72.5$ AP and $75.8$ AP on COCO validation dataset respectively, with significant reduction in parameters ($\downarrow80.6\%$; $\downarrow$ $56.8\%$) and GFLOPs ($\downarrow$ $75.3\%$; $\downarrow$ $24.7\%$). Code is publicly available.

Xin Dong, Yaxin Zhu, Yupeng Zhang et al.

In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made it much easier to achieve this. Still, there may still be subtle differences between languages that are neglected when doing so. To address this, we present a semi-supervised adversarial training process that minimizes the maximal loss for label-preserving input perturbations. The resulting model then serves as a teacher to induce labels for unlabeled target language samples that can be used during further adversarial training, allowing us to gradually adapt our model to the target language. Compared with a number of strong baselines, we observe significant gains in effectiveness on document and intent classification for a diverse set of languages.

Zhigang Kan, Linbo Qiao, Sen Yang et al.

Event Extraction plays an important role in information-extraction to understand the world. Event extraction could be split into two subtasks: one is event trigger extraction, the other is event arguments extraction. However, the F-Score of event arguments extraction is much lower than that of event trigger extraction, i.e. in the most recent work, event trigger extraction achieves 80.7%, while event arguments extraction achieves only 58%. In pipelined structures, the difficulty of event arguments extraction lies in its lack of classification feature, and the much higher computation consumption. In this work, we proposed a novel Event Extraction approach based on multi-layer Dilate Gated Convolutional Neural Network (EE-DGCNN) which has fewer parameters. In addition, enhanced local information is incorporated into word features, to assign event arguments roles for triggers predicted by the first subtask. The numerical experiments demonstrated significant performance improvement beyond state-of-art event extraction approaches on real-world datasets. Further analysis of extraction procedure is presented, as well as experiments are conducted to analyze impact factors related to the performance improvement.

Sen Yang, Leyang Cui, Jun Xie et al.

Sentiment analysis provides a useful overview of customer review contents. Many review websites allow a user to enter a summary in addition to a full review. Intuitively, summary information may give additional benefit for review sentiment analysis. In this paper, we conduct a study to exploit methods for better use of summary information. We start by finding out that the sentimental signal distribution of a review and that of its corresponding summary are in fact complementary to each other. We thus explore various architectures to better guide the interactions between the two and propose a hierarchically-refined review-centric attention model. Empirical results show that our review-centric model can make better use of user-written summaries for review sentiment analysis, and is also more effective compared to existing methods when the user summary is replaced with summary generated by an automatic summarization system.

Hao Yu, Rong Jin, Sen Yang

Recent developments on large-scale distributed machine learning applications, e.g., deep neural networks, benefit enormously from the advances in distributed non-convex optimization techniques, e.g., distributed Stochastic Gradient Descent (SGD). A series of recent works study the linear speedup property of distributed SGD variants with reduced communication. The linear speedup property enable us to scale out the computing capability by adding more computing nodes into our system. The reduced communication complexity is desirable since communication overhead is often the performance bottleneck in distributed systems. Recently, momentum methods are more and more widely adopted in training machine learning models and can often converge faster and generalize better. For example, many practitioners use distributed SGD with momentum to train deep neural networks with big data. However, it remains unclear whether any distributed momentum SGD possesses the same linear speedup property as distributed SGD and has reduced communication complexity. This paper fills the gap by considering a distributed communication efficient momentum SGD method and proving its linear speedup property.

Hao Yu, Sen Yang, Shenghuo Zhu

In distributed training of deep neural networks, parallel mini-batch SGD is widely used to speed up the training process by using multiple workers. It uses multiple workers to sample local stochastic gradient in parallel, aggregates all gradients in a single server to obtain the average, and update each worker's local model using a SGD update with the averaged gradient. Ideally, parallel mini-batch SGD can achieve a linear speed-up of the training time (with respect to the number of workers) compared with SGD over a single worker. However, such linear scalability in practice is significantly limited by the growing demand for gradient communication as more workers are involved. Model averaging, which periodically averages individual models trained over parallel workers, is another common practice used for distributed training of deep neural networks since (Zinkevich et al. 2010) (McDonald, Hall, and Mann 2010). Compared with parallel mini-batch SGD, the communication overhead of model averaging is significantly reduced. Impressively, tremendous experimental works have verified that model averaging can still achieve a good speed-up of the training time as long as the averaging interval is carefully controlled. However, it remains a mystery in theory why such a simple heuristic works so well. This paper provides a thorough and rigorous theoretical study on why model averaging can work as well as parallel mini-batch SGD with significantly less communication overhead.