Searcharxiv⌕ Search

arXiv subjects

Xu Sun

Publications and source records attributed to Xu Sun.

At least 127 records · Page 7Linked to original sources
arXiv2021

Long-term, Short-term and Sudden Event: Trading Volume Movement Prediction with Graph-based Multi-view Modeling

Trading volume movement prediction is the key in a variety of financial applications. Despite its importance, there is few research on this topic because of its requirement for comprehensive understanding of information from different sources. For instance, the relation between multiple stocks, recent transaction data and suddenly released events are all essential for understanding trading market. However, most of the previous methods only take the fluctuation information of the past few weeks into consideration, thus yielding poor performance. To handle this issue, we propose a graphbased approach that can incorporate multi-view information, i.e., long-term stock trend, short-term fluctuation and sudden events information jointly into a temporal heterogeneous graph. Besides, our method is equipped with deep canonical analysis to highlight the correlations between different perspectives of fluctuation for better prediction. Experiment results show that our method outperforms strong baselines by a large margin.

q-fin.ST↗
arXiv2021

Learning Relation Alignment for Calibrated Cross-modal Retrieval

Despite the achievements of large-scale multimodal pre-training approaches, cross-modal retrieval, e.g., image-text retrieval, remains a challenging task. To bridge the semantic gap between the two modalities, previous studies mainly focus on word-region alignment at the object level, lacking the matching between the linguistic relation among the words and the visual relation among the regions. The neglect of such relation consistency impairs the contextualized representation of image-text pairs and hinders the model performance and the interpretability. In this paper, we first propose a novel metric, Intra-modal Self-attention Distance (ISD), to quantify the relation consistency by measuring the semantic distance between linguistic and visual relations. In response, we present Inter-modal Alignment on Intra-modal Self-attentions (IAIS), a regularized training method to optimize the ISD and calibrate intra-modal self-attentions from the two modalities mutually via inter-modal alignment. The IAIS regularizer boosts the performance of prevailing models on Flickr30k and MS COCO datasets by a considerable margin, which demonstrates the superiority of our approach.

cs.CL↗
arXiv2021

Alleviating the Knowledge-Language Inconsistency: A Study for Deep Commonsense Knowledge

Knowledge facts are typically represented by relational triples, while we observe that some commonsense facts are represented by the triples whose forms are inconsistent with the expression of language. This inconsistency puts forward a challenge for pre-trained language models to deal with these commonsense knowledge facts. In this paper, we term such knowledge as deep commonsense knowledge and conduct extensive exploratory experiments on it. We show that deep commonsense knowledge occupies a significant part of commonsense knowledge while conventional methods fail to capture it effectively. We further propose a novel method to mine the deep commonsense knowledge distributed in sentences, alleviating the reliance of conventional methods on the triple representation form of knowledge. Experiments demonstrate that the proposal significantly improves the performance in mining deep commonsense knowledge.

cs.CL↗
arXiv2021

Rethinking Skip Connection with Layer Normalization in Transformers and ResNets

Skip connection, is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due to non-linearity by propagating a linear component through the neural network layers. However, from another point of view, it can also be seen as a modulating mechanism between the input and the output, with the input scaled by a pre-defined value one. In this work, we investigate how the scale factors in the effectiveness of the skip connection and reveal that a trivial adjustment of the scale will lead to spurious gradient exploding or vanishing in line with the deepness of the models, which could be addressed by normalization, in particular, layer normalization, which induces consistent improvements over the plain skip connection. Inspired by the findings, we further propose to adaptively adjust the scale of the input by recursively applying skip connection with layer normalization, which promotes the performance substantially and generalizes well across diverse tasks including both machine translation and image classification datasets.

cs.LG↗
arXiv2021

Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific trigger word inserted. Previous backdoor attacking methods usually assume that attackers have a certain degree of data knowledge, either the dataset which users would use or proxy datasets for a similar task, for implementing the data poisoning procedure. However, in this paper, we find that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples. Experimental results on sentiment analysis and sentence-pair classification tasks show that our method is more efficient and stealthier. We hope this work can raise the awareness of such a critical security risk hidden in the embedding layers of NLP models. Our code is available at https://github.com/lancopku/Embedding-Poisoning.

cs.CL↗
arXiv2021

Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network

Clustering is one of the fundamental problems in unsupervised learning. Recent deep learning based methods focus on learning clustering oriented representations. Among those methods, Variational Deep Embedding achieves great success in various clustering tasks by specifying a Gaussian Mixture prior to the latent space. However, VaDE suffers from two problems: 1) it is fragile to the input noise; 2) it ignores the locality information between the neighboring data points. In this paper, we propose a joint learning framework that improves VaDE with a robust embedding discriminator and a local structure constraint, which are both helpful to improve the robustness of our model. Experiment results on various vision and textual datasets demonstrate that our method outperforms the state-of-the-art baseline models in all metrics. Further detailed analysis shows that our proposed model is very robust to the adversarial inputs, which is a desirable property for practical applications.

cs.LG↗
arXiv2021

Collaborative Group Learning

Collaborative learning has successfully applied knowledge transfer to guide a pool of small student networks towards robust local minima. However, previous approaches typically struggle with drastically aggravated student homogenization when the number of students rises. In this paper, we propose Collaborative Group Learning, an efficient framework that aims to diversify the feature representation and conduct an effective regularization. Intuitively, similar to the human group study mechanism, we induce students to learn and exchange different parts of course knowledge as collaborative groups. First, each student is established by randomly routing on a modular neural network, which facilitates flexible knowledge communication between students due to random levels of representation sharing and branching. Second, to resist the student homogenization, students first compose diverse feature sets by exploiting the inductive bias from sub-sets of training data, and then aggregate and distill different complementary knowledge by imitating a random sub-group of students at each time step. Overall, the above mechanisms are beneficial for maximizing the student population to further improve the model generalization without sacrificing computational efficiency. Empirical evaluations on both image and text tasks indicate that our method significantly outperforms various state-of-the-art collaborative approaches whilst enhancing computational efficiency.

cs.LG↗
arXiv2021

Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation

Neural dialogue models suffer from low-quality responses when interacted in practice, demonstrating difficulty in generalization beyond training data. Recently, knowledge distillation has been used to successfully regularize the student by transferring knowledge from the teacher. However, the teacher and the student are trained on the same dataset and tend to learn similar feature representations, whereas the most general knowledge should be found through differences. The finding of general knowledge is further hindered by the unidirectional distillation, as the student should obey the teacher and may discard some knowledge that is truly general but refuted by the teacher. To this end, we propose a novel training framework, where the learning of general knowledge is more in line with the idea of reaching consensus, i.e., finding common knowledge that is beneficial to different yet all datasets through diversified learning partners. Concretely, the training task is divided into a group of subtasks with the same number of students. Each student assigned to one subtask not only is optimized on the allocated subtask but also imitates multi-view feature representation aggregated from other students (i.e., student peers), which induces students to capture common knowledge among different subtasks and alleviates the over-fitting of students on the allocated subtasks. To further enhance generalization, we extend the unidirectional distillation to the bidirectional distillation that encourages the student and its student peers to co-evolve by exchanging complementary knowledge with each other. Empirical results and analysis demonstrate that our training framework effectively improves the model generalization without sacrificing training efficiency.

cs.CL↗
arXiv2021

A representation formula for the probability density in stochastic dynamical systems with memory

Marcus stochastic delay differential equations (SDDEs) are often used to model stochastic dynamical systems with memory in science and engineering. Since no infinitesimal generators exist for Marcus SDDEs due to the non-Markovian property, conventional Fokker-Planck equations, which govern the evolution behavior of density, are not available for Marcus SDDEs. In this paper, we identify the Marcus SDDE with some Marcus stochastic differential equation (SDE) without delays but subject to extra constraints. This provides an efficient way to establish existence and uniqueness for the solution, and obtain a representation formula for probability density of the Marcus SDDE. In the formula, the probability density for Marcus SDDE is expressed in terms of that for Marcus SDE without delay.

math.DS↗
arXiv2020

EQG-RACE: Examination-Type Question Generation

Question Generation (QG) is an essential component of the automatic intelligent tutoring systems, which aims to generate high-quality questions for facilitating the reading practice and assessments. However, existing QG technologies encounter several key issues concerning the biased and unnatural language sources of datasets which are mainly obtained from the Web (e.g. SQuAD). In this paper, we propose an innovative Examination-type Question Generation approach (EQG-RACE) to generate exam-like questions based on a dataset extracted from RACE. Two main strategies are employed in EQG-RACE for dealing with discrete answer information and reasoning among long contexts. A Rough Answer and Key Sentence Tagging scheme is utilized to enhance the representations of input. An Answer-guided Graph Convolutional Network (AG-GCN) is designed to capture structure information in revealing the inter-sentences and intra-sentence relations. Experimental results show a state-of-the-art performance of EQG-RACE, which is apparently superior to the baselines. In addition, our work has established a new QG prototype with a reshaped dataset and QG method, which provides an important benchmark for related research in future work. We will make our data and code publicly available for further research.

cs.CL↗
arXiv2020

Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption

We argue that the vulnerability of model parameters is of crucial value to the study of model robustness and generalization but little research has been devoted to understanding this matter. In this work, we propose an indicator to measure the robustness of neural network parameters by exploiting their vulnerability via parameter corruption. The proposed indicator describes the maximum loss variation in the non-trivial worst-case scenario under parameter corruption. For practical purposes, we give a gradient-based estimation, which is far more effective than random corruption trials that can hardly induce the worst accuracy degradation. Equipped with theoretical support and empirical validation, we are able to systematically investigate the robustness of different model parameters and reveal vulnerability of deep neural networks that has been rarely paid attention to before. Moreover, we can enhance the models accordingly with the proposed adversarial corruption-resistant training, which not only improves the parameter robustness but also translates into accuracy elevation.

cs.LG↗
arXiv2020

A Backbone Replaceable Fine-tuning Framework for Stable Face Alignment

Heatmap regression based face alignment has achieved prominent performance on static images. However, the stability and accuracy are remarkably discounted when applying the existing methods on dynamic videos. We attribute the degradation to random noise and motion blur, which are common in videos. The temporal information is critical to address this issue yet not fully considered in the existing works. In this paper, we visit the video-oriented face alignment problem in two perspectives: detection accuracy prefers lower error for a single frame, and detection consistency forces better stability between adjacent frames. On this basis, we propose a Jitter loss function that leverages temporal information to suppress inaccurate as well as jittered landmarks. The Jitter loss is involved in a novel framework with a fine-tuning ConvLSTM structure over a backbone replaceable network. We further demonstrate that accurate and stable landmarks are associated with different regions with overlaps in a canonical coordinate, based on which the proposed Jitter loss facilitates the optimization process during training. The proposed framework achieves at least 40% improvement on stability evaluation metrics while enhancing detection accuracy versus state-of-the-art methods. Generally, it can swiftly convert a landmark detector for facial images to a better-performing one for videos without retraining the entire model.

cs.CV↗
arXiv2020

CAPT: Contrastive Pre-Training for Learning Denoised Sequence Representations

Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise, such as masking, shuffling, or substitution, and then try to recover the original input. However, such pre-training approaches are prone to learning representations that are covariant with the noise, leading to the discrepancy between the pre-training and fine-tuning stage. To remedy this, we present ContrAstive Pre-Training (CAPT) to learn noise invariant sequence representations. The proposed CAPT encourages the consistency between representations of the original sequence and its corrupted version via unsupervised instance-wise training signals. In this way, it not only alleviates the pretrain-finetune discrepancy induced by the noise of pre-training, but also aids the pre-trained model in better capturing global semantics of the input via more effective sentence-level supervision. Different from most prior work that focuses on a particular modality, comprehensive empirical evidence on 11 natural language understanding and cross-modal tasks illustrates that CAPT is applicable for both language and vision-language tasks, and obtains surprisingly consistent improvement, including 0.6\% absolute gain on GLUE benchmarks and 0.8\% absolute increment on $\text{NLVR}^2$.

cs.CL↗
arXiv2020

Memorized Sparse Backpropagation

Neural network learning is usually time-consuming since backpropagation needs to compute full gradients and backpropagate them across multiple layers. Despite its success of existing works in accelerating propagation through sparseness, the relevant theoretical characteristics remain under-researched and empirical studies found that they suffer from the loss of information contained in unpropagated gradients. To tackle these problems, this paper presents a unified sparse backpropagation framework and provides a detailed analysis of its theoretical characteristics. Analysis reveals that when applied to a multilayer perceptron, our framework essentially performs gradient descent using an estimated gradient similar enough to the true gradient, resulting in convergence in probability under certain conditions. Furthermore, a simple yet effective algorithm named memorized sparse backpropagation (MSBP) is proposed to remedy the problem of information loss by storing unpropagated gradients in memory for learning in the next steps. Experimental results demonstrate that the proposed MSBP is effective to alleviate the information loss in traditional sparse backpropagation while achieving comparable acceleration.

cs.LG↗
arXiv2020

Regularizing Dialogue Generation by Imitating Implicit Scenarios

Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario. To enable responses that are more meaningful and context-specific, we propose to improve generative dialogue systems from the scenario perspective, where both dialogue history and future conversation are taken into account to implicitly reconstruct the scenario knowledge. More importantly, the conversation scenarios are further internalized using imitation learning framework, where the conventional dialogue model that has no access to future conversations is effectively regularized by transferring the scenario knowledge contained in hierarchical supervising signals from the scenario-based dialogue model, so that the future conversation is not required in actual inference. Extensive evaluations show that our approach significantly outperforms state-of-the-art baselines on diversity and relevance, and expresses scenario-specific knowledge.

cs.CL↗
arXiv2020

Graph-based Multi-hop Reasoning for Long Text Generation

Long text generation is an important but challenging task.The main problem lies in learning sentence-level semantic dependencies which traditional generative models often suffer from. To address this problem, we propose a Multi-hop Reasoning Generation (MRG) approach that incorporates multi-hop reasoning over a knowledge graph to learn semantic dependencies among sentences. MRG consists of twoparts, a graph-based multi-hop reasoning module and a path-aware sentence realization module. The reasoning module is responsible for searching skeleton paths from a knowledge graph to imitate the imagination process in the human writing for semantic transfer. Based on the inferred paths, the sentence realization module then generates a complete sentence. Unlike previous black-box models, MRG explicitly infers the skeleton path, which provides explanatory views tounderstand how the proposed model works. We conduct experiments on three representative tasks, including story generation, review generation, and product description generation. Automatic and manual evaluation show that our proposed method can generate more informative and coherentlong text than strong baselines, such as pre-trained models(e.g. GPT-2) and knowledge-enhanced models.

cs.CL↗
arXiv2020

Investigation of the elliptic flow fluctuations of the identified particles using the A Multi-Phase Transport model

A Multi-Phase Transport (AMPT) model is used to study the elliptic flow fluctuations of identified particles using participant and spectator event planes. The elliptic flow measured using the first order spectator event plane is expected to give the elliptic flow relative to the true reaction plane which suppresses the flow fluctuations. However, the elliptic flow measured using the second-order participant plane is expected to capture the elliptic flow fluctuations. Our study shows that the first order spectator event plane could be used to study the elliptic flow fluctuations of the identified particles in the AMPT model. The elliptic flow fluctuations magnitude shows weak particle species dependence and transverse momentum dependence. Such observation will have important implications for understanding the source of the elliptic flow fluctuations.

nucl-ex↗