United States

Pre-trained language models have achieved state-of-the-art accuracies on various text classification tasks, e.g., sentiment analysis, natural language inference, and semantic textual similarity. However, the reliability of the fine-tuned text classifiers is an often underlooked performance criterion. For instance, one may desire a model that can detect out-of-distribution (OOD) samples (drawn far from training distribution) or be robust against domain shifts. We claim that one central obstacle to the reliability is the over-reliance of the model on a limited number of keywords, instead of looking at the whole context. In particular, we find that (a) OOD samples often contain in-distribution keywords, while (b) cross-domain samples may not always contain keywords; over-relying on the keywords can be problematic for both cases. In light of this observation, we propose a simple yet effective fine-tuning method, coined masked keyword regularization (MASKER), that facilitates context-based prediction. MASKER regularizes the model to reconstruct the keywords from the rest of the words and make low-confidence predictions without enough context. When applied to various pre-trained language models (e.g., BERT, RoBERTa, and ALBERT), we demonstrate that MASKER improves OOD detection and cross-domain generalization without degrading classification accuracy. Code is available at https://github.com/alinlab/MASKER.

AAAI 2021

MASKER: Masked Keyword Regularization for Reliable Text Classification

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

ACL 2022

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). 

technical paper

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. 

Unsupervised domain adaptation (UDA) assumes that source and target domain data are freely available and usually trained together to reduce the domain gap. However, considering the data privacy and the inefficiency of data transmission, it is impractical in real scenarios. Hence, it draws our eyes to optimize the network in the target domain without accessing labeled source data. To explore this direction in object detection, for the first time, we propose a source data-free domain adaptive object detection (SFOD) framework via modeling it into a problem of learning with noisy labels. Generally, a straightforward method is to leverage the pre-trained network from the source domain to generate the pseudo labels for target domain optimization. However, it is difficult to evaluate the quality of pseudo labels since no labels are available in target domain. In this paper, self-entropy descent (SED) is a metric proposed to search an appropriate confidence threshold for reliable pseudo label generation without using any handcrafted labels. Nonetheless, completely clean labels are still unattainable. After a thorough experimental analysis, false negatives are found to dominate in the generated noisy labels. Undoubtedly, false negatives mining is helpful for performance improvement, and we ease it to false negatives simulation through data augmentation like Mosaic. Extensive experiments conducted in four representative adaptation tasks have demonstrated that the proposed framework can easily achieve state-of-the-art performance. From another view, it also reminds the UDA community that the labeled source data are not fully exploited in the existing methods.

A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data

Modeling non-linear data as symmetric positive definite (SPD) matrices on Riemannian manifolds has attracted much attention for various classification tasks. In the context of deep learning, SPD matrix-based Riemannian networks have been shown to be a promising solution for classifying electroencephalogram (EEG) signals, capturing the Riemannian geometry within their structured 2D feature representation. However, existing approaches usually learn spatial-temporal structures in an embedding space for all available EEG signals, and their optimization procedures rely on computationally expensive iterations. Furthermore, these approaches often struggle to encode all of the various types of relationships into a single distance metric, resulting in a loss of generality. To address the above limitations, we propose a Riemannian Embedding Banks method, which divides the problem of common spatial patterns learning in an entire embedding space into K-subproblems and builds one model for each subproblem, to be combined with SPD neural networks. By leveraging the concept of the "separate to learn" technology on a Riemannian manifold, REB divides the data and the embedding space into K non-overlapping subsets and learns K separate distance metrics in a Riemannian geometric space instead of the vector space. Then, the learned K non-overlapping subsets are grouped into neurons in the SPD neural network's embedding layer. Experimental results on public EEG datasets demonstrate the superiority of the proposed approach for learning common spatial patterns of EEG signals despite their non-stationary nature, increasing the convergence speed while maintaining generalization.

Riemannian Embedding Banks for Common Spatial Patterns with EEG-Based SPD Neural Networks

Data augmentation is one of the most effective ways to stabilize learning by improving the generalization of machine-learning models. In recent years, automatic data augmentation methods, such as AutoAugment or Fast AutoAugment have been attracting attention; and these methods improved the results of image classification and object detection tasks. However, several problems remain. Most notably, a larger training dataset requires higher computational costs. When searching with a small dataset in an attempt to determine the data augmentation approach, the true data space and sampling data space do not fully correspond with each other, thereby causing the generalization performance to deteriorate. Moreover, in the existing automatic augmentation methods, the search phase is often dominated by an exceptional sub-policy, which results in a loss of diversity of operations. In this study, we solved these problems by introducing evolutionary computation to previous methods. As mentioned earlier, maintaining diversity is essential. Therefore, we adopted the thermodynamical genetic algorithm (TDGA), which can control the population diversity with a specific genetic operator, known as the thermodynamical selection rule. To confirm the effectiveness of the proposed method, computational experiments were conducted using two benchmark datasets, CIFAR-10 and SVHN, as examples. The experimental results show that the proposed method can obtain various useful augmentation sub-policies for the problems while reducing the computational cost.

Evolutionary Approach for Autoaugment Using the Thermodynamical Genetic Algorithm

Generative Adversarial Networks (GANs) have shown impressive gains in image synthesis. GAN inversion was recently studied to understand and utilize the knowledge it learns, where a real image is inverted back to a latent code and can thus be reconstructed by the generator. Although increasing the number of latent codes can improve inversion quality to a certain extent, we find that important details may still be neglected when performing feature composition over all the intermediate feature channels. To address this issue, we propose a Prior multi-Subspace Feature Composition (PmSFC) approach for high-fidelity inversion. Considering that the intermediate features are highly correlated with each other, we incorporate a self-expressive layer in the generator to discover meaningful subspaces. In this case, the features at a channel can be expressed as a linear combination of those at other channels in the same subspace. We perform feature composition separately in the subspaces. The semantic differences between them benefit the inversion quality, since the inversion process is regularized based on different aspects of semantics. In the experiments, the superior performance of PmSFC demonstrates the effectiveness of prior subspaces in facilitating GAN inversion together with extended applications in visual manipulation.

High Fidelity GAN Inversion via Prior Multi-Subspace Feature Composition

Graph-structured data is ubiquitous throughout the natural and social sciences, ranging from complex drug molecules to artificial neural networks. Evaluating their functional properties, e.g., drug effectiveness and prediction accuracy, is usually costly in terms of time, money, energy, or environment, becoming a bottleneck for the graph generation task. In this work, from the perspective of saving cost, we propose a novel Cost-Aware Graph Generation (CAGG) framework to generate graphs with optimal properties at as low cost as possible. By introducing a robust Bayesian graph neural network as the surrogate model and a goal-oriented training scheme for the generation model, the CAGG can approach the real expensive evaluation function and generate search space close to the optimal property, to avoid unnecessary evaluations. Intensive experiments conducted on two challenging real-world applications, including molecular discovery and neural architecture search, demonstrate its effectiveness and applicability. The results show that it can generate the optimal graphs and reduce the evaluation costs significantly compared to the state-of-the-art.

Cost-Aware Graph Generation: A Deep Bayesian Optimization Approach

Federated Learning (FL) is a promising machine learning paradigm that enables the analyzer to train a model without collecting users' raw data. To ensure users' privacy, differentially private federated learning has been intensively studied. The existing works are mainly based on the curator model or local model of differential privacy. However, both of them have pros and cons. The curator model allows greater accuracy but requires a trusted analyzer.  In the local model where users randomize local data before sending them to the analyzer, a trusted analyzer is not required but the accuracy is limited. In this work, by leveraging the \textit{privacy amplification} effect in the recently proposed shuffle model of differential privacy, we achieve the best of two worlds, i.e., accuracy in the curator model and strong privacy without relying on any trusted party. We first propose an FL framework in the shuffle model and a simple protocol (SS-Simple) extended from existing work. We find that SS-Simple only provides an insufficient privacy amplification effect in FL since the dimension of the model parameter is quite large. To solve this challenge, we propose an enhanced protocol (SS-Double) to increase the privacy amplification effect by subsampling. Furthermore, for boosting the utility when the model size is greater than the user population, we propose an advanced protocol (SS-Topk) with gradient sparsification techniques. We also provide theoretical analysis and numerical evaluations of the privacy amplification of the proposed protocols. Experiments on real-world dataset validate that SS-Topk improves the testing accuracy by 60.7% than the local model based FL. We highlight an observation that SS-Topk improves the accuracy by 33.94\% than the curator model based FL without any trusted party. Compared with non-private FL, our protocol SS-Topk only lose 1.48% accuracy under (2.348, 5e-6)-DP per epoch.

FLAME: Differentially Private Federated Learning in the Shuffle Model

Salient object location and segmentation are two different tasks in salient object detection (SOD). The former aims to globally find the most attractive objects in an image, whereas the latter can be achieved only using local regions that contain salient objects. However, previous methods mainly accomplish the two tasks simultaneously in a simple end-to-end manner, which leads to the ignorance of the differences between them. We assume that the human vision system orderly locates and segments objects, so we propose a novel progressive architecture with knowledge review network (PA-KRN) for SOD. It consists of three parts. (1) A coarse locating module (CLM) that uses body-attention label locates rough areas containing salient objects without boundary details. (2) An attention-based sampler highlights salient object regions with high resolution based on body-attention maps. (3) A fine segmenting module (FSM) finely segments salient objects. The networks applied in CLM and FSM are mainly based on our proposed knowledge review network (KRN) that utilizes the finest feature maps to reintegrate all previous layers, which can make up for the important information that is continuously diluted in the top-down path. Experiments on five benchmarks demonstrate that our single KRN can outperform state-of-the-art methods. Furthermore, our PA-KRN performs better and substantially surpasses the aforementioned methods.

Locate Globally, Segment Locally: A Progressive Architecture with Knowledge Review Network for Salient Object Detection

Continual relation extraction is an important task that focuses on extracting new facts incrementally from unstructured text. 
Given the sequential arrival order of the relations, this task is prone to two serious challenges, namely catastrophic forgetting and order-sensitivity. We propose a novel curriculum-meta learning method to tackle the above two challenges in continual relation extraction. We combine meta learning and curriculum learning to quickly adapt model parameters to a new task and to reduce interference of previously seen tasks on the current task. 
We design a novel relation representation learning method through the distribution of domain and range types of relations. 
Such representations are utilized to quantify the difficulty of tasks for the construction of curricula. Moreover, we also present novel difficulty-based metrics to quantitatively measure the extent of order-sensitivity of a given model, suggesting new ways to evaluate model robustness. 
Our comprehensive experiments on three benchmark datasets show that our proposed method outperforms the state-of-the-art techniques. 
The code is available at the anonymous GitHub repository: https://github.com/wutong8023/AAAI_CML.

Curriculum-Meta Learning for Order-Robust Continual Relation Extraction

In this paper, we propose a novel text-based talking-head video generation framework that synthesizes high-fidelity facial expressions and head motions in accordance with contextual sentiments as well as speech rhythm and pauses. To be specific, our framework consists of a speaker-independent stage and a speaker-specific stage. In the speaker-independent stage, we design three parallel networks to generate animation parameters of the mouth, upper face, and head from texts, separately. In the speaker-specific stage, we present a 3D face model guided attention network to synthesize videos tailored for different individuals. It takes the animation parameters as input and exploits an attention mask to manipulate facial expression changes for the input individuals. Furthermore, to better establish authentic correspondences between visual motions (i.e., facial expression changes and head movements) and audios, we leverage a high-accuracy motion capture dataset instead of relying on long videos of specific individuals. After attaining the visual and audio correspondences, we can effectively train our network in an end-to-end fashion. Extensive experiments on qualitative and quantitative results demonstrate that our algorithm achieves high-quality photo-realistic talking-head videos including various facial expressions and head motions according to speech rhythms and outperforms the state-of-the-art.

Write-a-Speaker: Text-Based Emotional and Rhythmic Talking-Head Generation

We present a method for learning dynamics of complex physical processes described by time-dependent nonlinear partial differential equations (PDEs). Our particular interest lies in extrapolating solutions in time beyond the range of temporal domain used in training. Our choice for a baseline method is physics-informed neural network (PINN) because the method parameterizes not only the solutions, but also the equations that describe the dynamics of physical processes. We demonstrate that PINN performs poorly on extrapolation tasks in many benchmark problems. To address this, we propose a novel method for better training PINN and demonstrate that our newly enhanced PINNs can accurately extrapolate solutions in time. Our method shows up to 72% smaller errors than state-of-the-art methods in terms of the standard L2-norm metric.

Downloads

Next from AAAI 2021

A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data

Similar lecture

Domain Representative Keywords Selection: A Probabilistic Approach

.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

A Free Lunch for Unsupervised Domain Adaptive Object Detection without Source Data

Similar lecture

Domain Representative Keywords Selection: A Probabilistic Approach

Downloads