United States

Second-order optimization methods have the ability to accelerate convergence by modifying the gradient through the curvature matrix. There have been many attempts to use second-order optimization methods for training deep neural networks. In this work, inspired by diagonal approximations and factored approximations such as Kronecker-factored Approximate Curvature (KFAC), we propose a new approximation to the Fisher information matrix (FIM) called Trace-restricted Kronecker-factored Approximate Curvature (TKFAC), which can hold the certain trace relationship between the exact and the approximate FIM. In TKFAC, we decompose each block of the approximate FIM as a Kronecker product of two smaller matrices and scaled by a coefficient related to trace. We theoretically analyze TKFAC&#39;s approximation error and give an upper bound of it. We also propose a new damping technique for TKFAC on convolutional neural networks to maintain the superiority of second-order optimization methods during training. Experiments show that our method has better performance compared with several state-of-the-art algorithms on some deep network architectures.

AAAI 2021

A Trace-Restricted Kronecker-Factored Approximation to Natural Gradient

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. 

Second-order optimization methods have the ability to accelerate convergence by modifying the gradient through the curvature matrix. There have been many attempts to use second-order optimization methods for training deep neural networks. In this work, inspired by diagonal approximations and factored approximations such as Kronecker-factored Approximate Curvature (KFAC), we propose a new approximation to the Fisher information matrix (FIM) called Trace-restricted Kronecker-factored Approximate Curvature (TKFAC), which can hold the certain trace relationship between the exact and the approximate FIM. In TKFAC, we decompose each block of the approximate FIM as a Kronecker product of two smaller matrices and scaled by a coefficient related to trace. We theoretically analyze TKFAC's approximation error and give an upper bound of it. We also propose a new damping technique for TKFAC on convolutional neural networks to maintain the superiority of second-order optimization methods during training. Experiments show that our method has better performance compared with several state-of-the-art algorithms on some deep network architectures.

technical paper

A simile is a figure of speech that directly makes a comparison, showing similarities between two different things, e.g. ``Reading papers can be dull sometimes,like watching grass grow". Human writers often interpolate appropriate similes into proper locations of the plain text to vivify their writings. However, none of existing work has explored neural simile interpolation, including both locating and generation. In this paper, we propose a new task of Writing Polishment with Simile (WPS) to investigate whether machines are able to polish texts with similes as we human do. Accordingly, we design a two-staged Locate&Gen model based on transformer architecture. Our model firstly locates where the simile interpolation should happen, and then generates a location-specific simile. We also release a large-scale Chinese Simile (CS) dataset containing 5 million similes with context. The experimental results demonstrate the feasibility of WPS task and shed light on the future research directions towards better automatic text polishment.

Writing Polishment with Simile: Task, Dataset and a Neural Approach

Lexically constrained sentence generation allows the incorporation of prior knowledge such as lexical constraints into the output. This technique has been applied to machine translation, and dialog response generation. Previous work usually used Markov Chain Monte Carlo (MCMC) sampling to generate lexically constrained sentences, but they randomly determined the position to be edited and the action to be taken, resulting in many invalid refinements. To overcome this challenge, we used a classifier to instruct the MCMC-based models where and how to refine the candidate sentences. First, we developed two methods to create synthetic data on which the pre-trained model is fine-tuned to obtain a reliable classifier. Next, we proposed a two-step approach, â€œPredict and Reviseâ€, for constrained sentence generation. During the predict step, we leveraged the classifier to compute the learned prior for the candidate sentence. During the revise step, we resorted to MCMC sampling to revise the candidate sentence by conducting a sampled action at a sampled position drawn from the learned prior. We compared our proposed models with many strong baselines on two tasks, generating sentences with lexical constraints and text infilling. Experimental results have demonstrated that our proposed model performs much better than the previous work in terms of sentence fluency and diversity. Our code, pre-trained models and Appendix are available at https://github.com/NLPCode/MCMCXLNet.

Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNet

Participatory budgeting is a method used by city governments to select public projects to fund based on residents' votes. Many cities use participatory budgeting at a district level. Typically, a budget is divided among districts proportionally to their population, and each district holds an election over local projects and then uses its budget to fund the projects most preferred by its voters. However, district-level participatory budgeting can yield poor social welfare because it does not necessarily fund projects supported across multiple districts. On the other hand, decision making that only takes global social welfare into account can be unfair to districts: A social-welfare-maximizing solution might not fund any of the projects preferred by a district, despite the fact that its constituents pay taxes to the city. Thus, we study how to fairly maximize social welfare in a participatory budgeting setting with a single city-wide election. We propose a notion of fairness that guarantees each district at least as much welfare as it would have received in a district-level election. We show that, although optimizing social welfare subject to this notion of fairness is NP-hard, we can efficiently construct a lottery over welfare-optimal outcomes that is fair in expectation. Moreover, we show that, when we are allowed to slightly relax fairness, we can efficiently compute a fair solution that is welfare-maximizing, but which may overspend the budget.

District-Fair Participatory Budgeting

This paper presents a simple unsupervised visual representation learning method with a pretext task of discriminating all images in a dataset using a parametric, instance-level classifier. The overall framework is a replica of a supervised classification model, where semantic classes (e.g., dog, bird, and ship) are replaced by instance IDs. However, scaling up the classification task from thousands of semantic labels to millions of instance labels brings specific challenges including 1) the large-scale softmax computation; 2) the slow convergence due to the infrequent visiting of instance samples; and 3) the massive number of negative classes that can be noisy. This work presents several novel techniques to handle these difficulties. First, we introduce a hybrid parallel training framework to make large-scale training feasible. Second, we present a raw-feature initialization mechanism for classification weights, which we assume offers a contrastive prior for instance discrimination and can clearly speed up converge in our experiments. Finally, we propose to smooth the labels of a few hardest classes to avoid optimizing over very similar negative pairs. While being conceptually simple, our framework achieves competitive or superior performance compared to state-of-the-art unsupervised approaches, i.e., SimCLR, MoCoV2, and PIC under ImageNet linear evaluation protocol and on several downstream visual tasks, verifying that full instance classification is a strong pretraining technique for many semantic visual tasks.

Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning

Network modeling aims to learn the latent representations of nodes such that the representations preserve both network structures and node attribute information. This problem is fundamental due to its prevalence in numerous domains. However, existing approaches either target the static networks or struggle to capture the complicated temporal dependency, while most real-world networks evolve over time and the success of network modeling hinges on the understanding of how entities are temporally connected. In this paper, we present TRRN, a transformer-style relational reasoning network with dynamic memory updating, to deal with the above challenges. TRRN employs multi-head self-attention to reason over a set of memories, which provides a multitude of shortcut paths for information to flow from past observations to the current latent representations. By utilizing the policy networks augmented with differentiable binary routers, TRRN estimates the possibility of each memory being activated and dynamically updates the memories at the time steps when they are most relevant. We evaluate TRRN with the tasks of node classification and link prediction on four real temporal network datasets. Experimental results demonstrate the consistent performance gains for TRRN over the leading competitors.

Transformer-Style Relational Reasoning with Dynamic Memory Updating for Temporal Network Modeling

Lexically constrained neural machine translation (NMT), which leverages pre-specified translation to constrain NMT, has practical significance in interactive translation and NMT domain adaption. Previous work either modify the decoding algorithm or train the model on augmented dataset. These methods suffer from either high computational overheads or low copying success rates. In this paper, we investigate Att-Input and Att-Output, two alignment-based constrained decoding methods. These two methods revise the target tokens during decoding based on word alignments derived from encoder-decoder attention weights. Our study shows that Att-Input translates better while Att-Output is more computationally efficient. Capitalizing on both strengths, we further propose EAM-Output by introducing an explicit alignment module (EAM) to a pretrained Transformer. It decodes similarly as EAM-Output, except using alignments derived from the EAM. We leverage the word alignments induced from Att-Input as labels and train the EAM while keeping the parameters of the Transformer frozen. Experiments on WMT16 De-En and WMT16 Ro-En show the effectiveness of our approaches on constrained NMT. In particular, the proposed EAM-Output method consistently outperforms previous approaches in translation quality, with light computational overheads over unconstrained baseline.

Lexically Constrained Neural Machine Translation with Explicit Alignment Guidance

Conversion rate (CVR) prediction is one of the most critical tasks for digital display advertising. Commercial systems often require to update models in an online learning manner to catch up with the evolving data distribution. However, conversions usually do not happen immediately after user clicks. This may result in inaccurate labeling, which is called delayed feedback problem. In previous studies, delayed feedback problem is handled either by waiting positive label for a long period of time, or by consuming the negative sample on its arrival and then insert a positive duplicate when conversion happens later. Indeed, there is a trade-off between waiting for more accurate labels and utilizing fresh data, which is not considered in existing works. To strike a balance in this trade-off, we propose Elapsed-Time Sampling Delayed Feedback Model (ES-DFM), which models the relationship between the observed conversion distribution and the true conversion distribution. Then we optimize the expectation of true conversion distribution via importance sampling under the elapsed-time sampling distribution. We further estimate the importance weight for each instance, which is used as the weight of loss function in CVR prediction. To demonstrate the effectiveness of ES-DFM, we conduct extensive experiments on a public data and a private industrial dataset. Experimental results confirm that our method consistently outperforms the previous state-of-the-art results.

Capturing Delayed Feedback in Conversion Rate Prediction via Elapsed-Time Sampling

Abnormal event detection in the surveillance video is an essential
but challenging task, and many methods have been
proposed to deal with this problem. The previous methods
either only consider the appearance information or directly
integrate the results of appearance and motion information
without considering their endogenous consistency
semantics explicitly. Inspired by the rule humans identify
the abnormal frames from multi-modality signals, we propose
an Appearance-Motion Memory Consistency Network
(AMMC-Net). Our method first makes full use of the prior
knowledge of appearance and motion signals to explicitly
capture the correspondence between them in the high-level
feature space. Then, it combines the multi-view features to
obtain a more essential and robust feature representation of
regular events, which can significantly increase the gap between
an abnormal and a regular event. In the anomaly detection
phase, we further introduce a commit error in the latent
space joint with the prediction error in pixel space to enhance
the detection accuracy. Solid experimental results on various
standard datasets validate the effectiveness of our approach.

Appearance-Motion Memory Consistency Network for Video Anomaly Detection

The fast development of neuromorphic hardwares promotes Spiking Neural Networks (SNNs) to a thrilling research avenue. Current SNNs, though much efficient, are less effective compared with leading Artificial Neural Networks (ANNs) especially in supervised learning tasks. Recent efforts further demonstrate the potential of SNNs in supervised learning by introducing  approximated  backpropagation (BP) methods. To deal with the non-differentiable spike function in SNNs, these BP methods utilize information from the spatio-temporal domain to adjust the model parameters. With the increasing of time window and network size, the computational complexity of spatio-temporal backpropagation augments dramatically. In this paper, we propose a new backpropagation method for SNNs based on the accumulated spiking flow (ASF), i.e. ASF-BP. In the proposed ASF-BP method, updating parameters does not rely on the spike train of spiking neurons but leverage accumulated inputs and outputs of spiking neurons over the time window, which reduces the BP complexity significantly. We further present an adaptive linear estimation model to approach the dynamic characteristics of spiking neurons statistically. Experimental results demonstrate that with our proposed ASF-BP method, light-weight convolutional SNNs achieve superior performances compared with other spike-based BP methods on both non-neuromorphic (MNIST, CIFAR10) and neuromorphic (CIFAR10-DVS) datasets. The code is available at https://github.com/neural-lab/ASF-BP.

Training Spiking Neural Networks with Accumulated Spiking Flow

We consider the models of deep multi-task learning with recurrent architectures that exploit regularities across tasks to improve the performance of multiple sequence processing tasks jointly. Most existing architectures are painstakingly customized to learn task relationships for different problems, which is not flexible enough to model the dynamic task relationships and lacks generalization abilities to novel test-time scenarios. We propose multi-task recurrent modular networks (MT-RMN) that can be incorporated in any multi-task recurrent models to address the above drawbacks. MT-RMN consists of a shared encoder and multiple task-specific decoders, and recurrently operates over time. For better flexibility, it modularizes the encoder into multiple layers of sub-networks and dynamically controls the connection between these sub-networks and the decoders at different time steps, which provides the recurrent networks with varying degrees of parameter sharing for tasks with dynamic relatedness. For the generalization ability, MT-RMN aims to discover a set of generalizable sub-networks in the encoder that are assembled in different ways for different tasks. The policy networks augmented with the differentiable routers are utilized to make the binary connection decisions between the sub-networks. The experimental results on three multi-task sequence processing datasets consistently demonstrate the effectiveness of MT-RMN.

Downloads

Next from AAAI 2021

Writing Polishment with Simile: Task, Dataset and a Neural Approach

Similar lecture

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

.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

Writing Polishment with Simile: Task, Dataset and a Neural Approach

Similar lecture

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

Downloads