United States

It is well-known that second-order optimizer can accelerate the training of deep neural networks, however, the huge computation cost of second-order optimization makes it impractical to apply in real practice. In order to reduce the cost, many methods have been proposed to approximate a second-order matrix. Inspired by KFAC, we propose a novel Trace-based Hardware-driven layer-ORiented Natural Gradient Descent Computation method, called THOR, to make the second-order optimization applicable in the real application models. Specifically, we gradually increase the update interval and use the matrix trace to determine which blocks of Fisher Information Matrix (FIM) need to be updated. Moreover, by resorting the power of hardware, we have designed a Hardware-driven approximation method for computing FIM to achieve better performance. To demonstrate the effectiveness of THOR, we have conducted extensive experiments. The results show that training ResNet-50 on ImageNet with THOR only takes 66.7 minutes to achieve a top-1 accuracy of 75.9 % under an 8 Ascend 910 environment with MindSpore, a new deep learning computing framework. Moreover, with more computational resources, THOR can only takes 2.7 minutes to 75.9 % with 256 Ascend 910.

AAAI 2021

THOR, Trace-Based Hardware-Driven Layer-Oriented Natural Gradient Descent Computation

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

technical paper

A well known result is that, given a consistent heuristic and no other source of information, A* does expand a minimal number of nodes up to tie-breaking. We extend this analysis for A* with dominance pruning, which exploits a dominance relation to eliminate some nodes during the search. We show that the expansion order of A* is not necessarily optimally efficient when considering dominance pruning with arbitrary dominance relations, but it remains optimally efficient under certain restrictions for the heuristic and dominance relation.

On the Optimal Efficiency of A* with Dominance Pruning

Modern  society  is  heavily  dependent  on  large  scale client-server  systems  with  applications  ranging  from Internet and Communication Services to sophisticated logistics and deployment of goods. To maintain and improve such a system, a careful study of client and server dynamics is needed â€“ e.g. response/service times, aver-age number of clients at given times, etc. To this end, one traditionally relies, within the queuing theory formalism,on parametric analysis and explicit distribution forms.However, parametric forms limit the modelâ€™s expressiveness and could struggle on extensively large datasets. We propose a novel data-driven approach towards queuing systems: the Deep Generative Service Times. Our methodology delivers a flexible and scalable model for service and response times. We leverage the representation capabilities of Recurrent Marked Point Processes for the temporal dynamics of clients, as well as Wasserstein Generative  Adversarial  Network  techniques,  to  learn deep generative models which are able to represent complex conditional service time distributions. We provide extensive experimental analysis on both empirical and synthetic datasets, showing the effectiveness of the proposed models

Learning Deep Generative Models for Queuing Systems

Recognition of human activities is an important task due to its far-reaching applications such as healthcare system, context-aware applications, and security monitoring. Recently, WiFi based human activity recognition (HAR) is becoming ubiquitous due to its non-invasiveness. Existing WiFi-based HAR methods regard WiFi signals as a temporal sequence of channel state information (CSI), and employ deep sequential models (e.g., RNN, LSTM) to automatically capture channel-over-time features. Although being remarkably effective, they suffer from two major drawbacks. Firstly, the granularity of a single temporal point is blindly elementary for representing meaningful CSI patterns.  Secondly, the time-over-channel features are also important, and could be a natural data augmentation. To address the drawbacks, we propose a novel Two-stream Convolution Augmented Human Activity Transformer (THAT) model. Our model proposes to utilize a two-stream structure to capture both time-over-channel and channel-over-time features, and use the multi-scale convolution augmented transformer to capture range-based patterns. Extensive experiments on four real experiment datasets demonstrate that our model outperforms state-of-the-art models in terms of both effectiveness and efficiency.

Two-Stream Convolution Augmented Transformer for Human Activity Recognition

Image-based virtual try-on aims to synthesize the customer image with an in-shop clothes image to acquire seamless and natural try-on results, which have attracted increasing attentions. The main procedures of image-based virtual try-on usually consist of clothes image generation and try-on image synthesis, whereas prior arts cannot guarantee satisfying clothes results when facing large geometric changes and complex clothes patterns, which further deteriorates the afterwards try-on results. To address this issue, we propose a novel virtual try-on network based on landmark-guided shape matching (LM-VTON). Specifically, the clothes image generation progressively learns the warped clothes and refined clothes in an end-to-end manner, where we introduce a landmark-based constraint in Thin-Plate Spline (TPS) warping to inject finer deformation constraints around the clothes. The try-on process synthesizes the warped clothes with personal characteristics via a semantic indicator. Qualitative and quantitative experiments on two public datasets validate the superiority of the proposed method, especially for challenging cases such as large geometric changes and complex clothes patterns.
Code will be available at https://github.com/lgqfhwy/LM-VTON.

Toward Realistic Virtual Try-On through Landmark Guided Shape Matching

News, as one of the fundamental social media types, typically contains both texts and images. Image selection, which involves choosing appropriate images according to some specified contexts, is crucial for formulating good news. However, it presents two challenges: where to place images and which images to use. The difficulties associated with this where-which problem lie in the fact that news typically contains linguistically rich text that delivers complex information and more than one image. In this paper, we propose a novel end-to-end two-stage framework to address these issues comprehensively. In the first stage, we identify key information in news by using location embeddings, which represent the local contextual information of each candidate location for image insertion. Then, in the second stage, we thoroughly examine the candidate images and select the most context-related ones to insert into each location identified in the first stage. We also introduce three insertion strategies to formulate different scenarios influencing the image selection procedure. Extensive experiments demonstrate the consistent superiority of the proposed framework in image selection.

News Content Completion with Location-Aware Image Selection

Automatic song writing aims to compose a song (lyric and/or melody) by machine, which is an interesting topic in both academia and industry. In automatic song writing, lyric-to-melody generation and melody-to-lyric generation are two important tasks, both of which usually suffer from the following challenges: 1) the paired lyric and melody data are limited, which affects the generation quality of the two tasks, considering a lot of paired training data are needed due to the weak correlation between lyric and melody; 2) Strict alignments are required between lyric and melody, which relies on specific alignment modeling. In this paper, we propose SongMASS to address the above challenges, which leverages masked sequence to sequence (MASS) pre-training and attention based alignment modeling for lyric-to-melody and melody-to-lyric generation. Specifically, 1) we extend the original sentence-level MASS pre-training to song level to better capture long contextual information in music, and use a separate encoder and decoder for each modality (lyric or melody);  2) we leverage sentence-level attention mask and token-level attention constraint during training to enhance the alignment between lyric and melody. During inference, we use a dynamic programming strategy to obtain the alignment between each word/syllable in lyric and note in melody. We pre-train SongMASS on unpaired lyric and melody datasets, and both objective and subjective evaluations demonstrate that SongMASS generates lyric and melody with significantly better quality than the baseline method.

SongMASS: Automatic Song Writing with Pre-Training and Alignment Constraint

Question generation is a challenging task and has attracted widespread attention in recent years. Although previous studies have made great progress, there are still two main shortcomings: First, previous work did not simultaneously capture the sequence information and structure information hidden in the context, which results in poor results of the generated questions. Second, the generated questions cannot be answered by the given context. To tackle these issues, we propose an entity guided question generation model with contextual structure information and sequence information capturing. We use a Graph Convolutional Network and a Bidirectional Long Short Term Memory Network to capture the structure information and sequence information of the context, simultaneously. In addition, to improve the answerability of the generated questions, we use an entity-guided approach to obtain question type from the answer, and jointly encode the answer and question type. Both automatic and manual metrics show that our model can generate comparable questions with state-of-the-art models. Our code is available at https://github.com/VISLANG-Lab/EGSS.

Entity Guided Question Generation with Contextual Structure and Sequence Information Capturing

Developing link prediction models to automatically complete knowledge graphs has recently been the focus of significant research interest. The current methods for the link prediction task have two natural problems: 1) the relation distributions in KGs are usually unbalanced, and 2) there are many unseen relations that occur in practical situations. These two problems limit the training effectiveness and practical applications of the existing link prediction models. We advocate a holistic understanding of KGs and we propose in this work a unified Generalized Relation Learning framework GRL to address the above two problems, which can be plugged into existing link prediction models. GRL conducts a generalized relation learning, which is aware of semantic correlations between relations that serve as a bridge to connect semantically similar relations. After training with GRL, the closeness of semantically similar relations in vector space and the discrimination of dissimilar relations are improved. We perform comprehensive experiments on six benchmarks to demonstrate the superior capability of GRL in the link prediction task. In particular, GRL is found to enhance the existing link prediction models making them insensitive to unbalanced relation distributions and capable of learning unseen relations.

Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction

Loss landscape analysis is extremely useful for a deeper understanding of the generalization ability of deep neural network models. In this work, we propose a layerwise loss landscape analysis where the loss surface at every layer is studied independently and also on how each correlates to the overall loss surface. We study the layerwise loss landscape by studying the eigenspectra of the Hessian at each layer. In particular, our results show that the layerwise Hessian geometry is largely similar to the entire Hessian. We also report an interesting phenomenon where the Hessian eigenspectrum of middle layers of the deep neural network are observed to most similar to the overall Hessian eigenspectrum. We also show that the maximum eigenvalue and the trace of the Hessian (both full network and layerwise) reduce as training of the network progresses. We leverage on these observations to propose a new regularizer based on the trace of the layerwise Hessian. Penalizing the trace of the Hessian at every layer indirectly forces Stochastic Gradient Descent to converge to flatter minima, which are shown to have better generalization performance. In particular, we show that such a layerwise regularizer can be leveraged to penalize the middlemost layers alone, which yields promising results. Our empirical studies on well-known deep nets across datasets support the claims of this work.

A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and Its Applications to Regularization

Defect prediction, the task of predicting the presence of defects in source code artifacts, has broad application in software development. Defect prediction faces two major challenges, label scarcity, where only a small percentage of code artifacts are labeled, and data imbalance, where the majority of labeled artifacts are non-defective. Moreover, current defect prediction methods ignore the impact of information propagation among code artifacts and this negligence leads to performance degradation. In this paper, we propose DPCAG, a novel model to address the above three issues. We treat code artifacts as nodes in a graph, and learn to propagate influence among neighboring nodes iteratively in an EM framework. DPCAG dynamically adjusts the contributions of each node and selects high-confidence nodes for data augmentation. Experimental results on real-world benchmark datasets show that DPCAG improves performance compare to the state-of-the-art models. In particular, DPCAG achieves substantial performance superiority when measured by Matthews Correlation Coefficient (MCC), a metric that is widely acknowledged to be the most suitable for imbalanced data.

Downloads

Next from AAAI 2021

On the Optimal Efficiency of A* with Dominance Pruning

Similar lecture

A Trace-Restricted Kronecker-Factored Approximation to Natural Gradient

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

On the Optimal Efficiency of A* with Dominance Pruning

Similar lecture

A Trace-Restricted Kronecker-Factored Approximation to Natural Gradient

Downloads