United States

Machine learning systems that built upon varying feature space are ubiquitous across the world. When the set of practical or virtual features changes, the online learning approach can adjust the learned model accordingly rather than re-training from scratch and has been an attractive area of research. Despite its importance, most studies for algorithms that are capable of handling online features have no ensurance of stationarity point convergence, while the accuracy guaranteed methods are still limited to some simple cases such as $\ell_1$ or $\ell_2$ norms with square loss. To address this challenging problem, we develop an efficient Dynamic Feature Learning System (DFLS) to perform online learning on the unfixed feature set for more general statistical models and demonstrate how DFLS opens up many new applications. We are the first to achieve accurate &amp; reliable feature-wise online learning for a broad class of models like logistic regression, spline interpolation, group Lasso and Poisson regression. By utilizing DFLS, the updated model is theoretically the same as the model trained from scratch using the entire new feature space. Specifically, we reparameterize the feature-varying procedure and devise the corresponding ordinary differential equation (ODE) system to compute the optimal solutions of the new model status. Simulation studies reveal that the proposed DFLS can substantially ease the computational cost without forgetting.

AAAI 2023

When Online Learning Meets ODE: Learning without Forgetting on Variable Feature Space

ml: optimization

ml: online learning & bandits

ml: lifelong and continual learning

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

Machine learning systems that built upon varying feature space are ubiquitous across the world. When the set of practical or virtual features changes, the online learning approach can adjust the learned model accordingly rather than re-training from scratch and has been an attractive area of research. Despite its importance, most studies for algorithms that are capable of handling online features have no ensurance of stationarity point convergence, while the accuracy guaranteed methods are still limited to some simple cases such as $\ell_1$ or $\ell_2$ norms with square loss. To address this challenging problem, we develop an efficient Dynamic Feature Learning System (DFLS) to perform online learning on the unfixed feature set for more general statistical models and demonstrate how DFLS opens up many new applications. We are the first to achieve accurate & reliable feature-wise online learning for a broad class of models like logistic regression, spline interpolation, group Lasso and Poisson regression. By utilizing DFLS, the updated model is theoretically the same as the model trained from scratch using the entire new feature space. Specifically, we reparameterize the feature-varying procedure and devise the corresponding ordinary differential equation (ODE) system to compute the optimal solutions of the new model status. Simulation studies reveal that the proposed DFLS can substantially ease the computational cost without forgetting.

poster

As the COVID-19 pandemic puts pressure on healthcare systems worldwide, the computed tomography image based AI diagnostic system has become a sustainable solution for early diagnosis. However, the model-wise vulnerability under adversarial perturbation hinders its deployment in practical situation. The existing adversarial training strategies are difficult to generalized into medical imaging field challenged by complex medical texture features. To overcome this challenge, we propose a Contour Attention Preserving (CAP) method based on lung cavity edge extraction. The contour prior features are injected to attention layer via a parameter regularization and we optimize the robust empirical risk with hybrid distance metric. We then introduce a new cross-nation CT scan dataset to evaluate the generalization capability of the adversarial robustness under distribution shift. Experimental results indicate that the proposed method achieves state-of-the-art performance in multiple adversarial defense and generalization tasks. The code and dataset are available at https://github.com/Quinn777/CAP.

Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection

Spatio-temporal prediction plays a critical role in smart city construction. Jointly modeling multiple spatio-temporal tasks can further promote an intelligent city life by integrating their inseparable relationship. However, existing studies fail to address this joint learning problem well, which generally solve tasks individually or a fixed task combination. The challenges lie in the tangled relation between different properties, the demand for supporting flexible combinations of tasks and the complex spatio-temporal dependency. To cope with the problems above, we propose an Automated Spatio-Temporal multi-task Learning (AutoSTL) method to handle multiple spatio-temporal tasks jointly. Firstly, we propose a scalable architecture consisting of advanced spatio-temporal operations to exploit the complicated dependency. Shared modules and feature fusion mechanism are incorporated to further capture the intrinsic relationship between tasks. Furthermore, our model automatically allocates the operations and fusion weight. Extensive experiments on benchmark datasets verified that our model achieves state-of-the-art performance. As we can know, AutoSTL is the first automated spatio-temporal multi-task learning method.

AutoSTL: Automated Spatio-Temporal Multi-Task Learning

Scene text image super-resolution (STISR) aims to simultaneously increase the resolution and legibility of the text images, and the resulting images will significantly affect the performance of downstream tasks. Although numerous progress has been made, existing approaches raise two crucial issues: (1) They neglect the global structure of the text, which bounds the semantic determinism of the scene text. (2) The priors, e.g., text prior or stroke prior, employed in existing works, are extracted from pre-trained text recognizers. That said, such priors suffer from the domain gap including low resolution and blurriness caused by poor imaging conditions, leading to incorrect guidance. Our work addresses these gaps and proposes a plug-and-play module dubbed as Dual Prior Modulation Network (DPMN), which leverages dual image-level priors to bring performance gain over existing approaches. Specifically, two types of prior-guided refinement modules, each using the text mask or graphic recognition result of the low-quality SR image from the preceding layer, are designed to improve the structural clarity and semantic accuracy of the text, respectively. The following attention mechanism hence modulates two quality-enhanced images to attain a superior SR result. Extensive experiments validate that our method improves the image quality and boosts the performance of downstream tasks over five typical approaches on the benchmark. Substantial visualizations and ablation studies demonstrate the advantages of the proposed DPMN. Code is available at: https://github.com/jdfxzzy/DPMN.

Improving Scene Text Image Super-Resolution via Dual Prior Modulation Network

Conversational contextual bandits elicit user preferences by occasionally querying for explicit feedback on key-terms to accelerate learning.  However, there are aspects of existing approaches which limit their performance. First, information gained from key-term-level conversations and arm-level recommendations is not appropriately incorporated to speed up learning. Second, it is important to ask explorative key-terms to quickly elicit the user's potential interests in various domains to accelerate the convergence of user preference estimation, which has never been considered in existing works.  To tackle these issues, we first propose ``ConLinUCB", a general framework for conversational bandits with better information incorporation, combining arm-level and key-term-level feedback to estimate user preference in one step at each time. Based on this framework, we further design two bandit algorithms with explorative key-term selection strategies, ConLinUCB-BS and ConLinUCB-MCR. We prove tighter regret upper bounds of our proposed algorithms. Particularly, ConLinUCB-BS achieves a regret bound of $O(\sqrt{dT\log T})$, better than the previous result $O(d\sqrt{T}\log T)$. Extensive experiments on synthetic and real-world data show significant advantages of our algorithms in learning accuracy (up to 54\% improvement) and computational efficiency (up to 72\% improvement), compared to the classic ConUCB algorithm, showing the potential benefit to recommender systems. 

Efficient Explorative Key-term Selection Strategies for Conversational Contextual Bandits

Few-shot slot tagging is an important task in dialogue systems and attracts much attention of researchers. Most previous few-shot slot tagging methods utilize meta-learning procedure for training and strive to construct a large number of different meta tasks to simulate the testing situation of insufficient data. However, there is a widespread phenomenon of overlap slot between two domains in slot tagging. Traditional meta tasks ignore this special phenomenon and cannot simulate such realistic few-shot slot tagging scenarios. It violates the basic principle of meta-learning which the meta task is consistent with the real testing task, leading to historical information forgetting problem. In this paper, we introduce a novel domain-transfer meta task design paradigm to tackle this problem. We distribute a basic domain to each target domain based on the coincidence degree of slot labels between these two domains. Unlike classic meta tasks which only rely on small samples of target domain, our meta tasks aim to correctly infer the class of target domain query samples based on both abundant data in basic domain and scarce data in target domain. To accomplish our meta task, we propose a Task Adaptation Network to effectively transfer the historical information from the basic domain to the target domain. We carry out sufficient experiments on the benchmark slot tagging dataset SNIPS and the name entity recognition dataset NER. Results demonstrate that our proposed model outperforms previous methods and achieves the state-of-the-art performance.

A Domain-Transfer Meta Task Design Paradigm for Few-Shot Slot Tagging

Multi-task learning models based on temporal smoothness assumption, in which each time point of a sequence of time points concerns a task of prediction, assume the adjacent tasks are similar to each other. However, the effect of outliers is not taken into account.  In this paper, we show that even only one outlier task will destroy the performance of the entire model.  To solve this problem, we propose two Robust Temporal Smoothness (RoTS) frameworks. Compared with the existing models based on temporal relation, our methods not only chase the temporal smoothness information; but identify outlier tasks, however, without increasing the computational complexity.  Detailed theoretical analyses are presented to evaluate the performance of our methods.  Experimental results on synthetic and real-life datasets demonstrate the effectiveness of our frameworks. We also discuss several potential specific applications and extensions of our RoTS frameworks.

Robust Temporal Smoothness in Multi-Task Learning

Sparse learning based feature selection has been widely investigated in recent years. In this study, we focus on the $ \ell_{2,0} $-norm based feature selection, which is effective for exact top-$ k $ feature selection but challenging to optimize. To solve the general $ \ell_{2,0} $-norm constrained problems, we novelly develop a parameter-free optimization framework based on the coordinate descend (CD) method, termed CD-LSR. Specifically, we devise a skillful conversion from the original problem to solving one continuous matrix and one discrete selection matrix. Then the nontrivial $ \ell_{2,0} $-norm constraint can be solved efficiently by solving the selection matrix with CD method. We impose the $ \ell_{2,0} $-norm on a vanilla least square regression (LSR) model for feature selection and optimize it with CD-LSR. Extensive experiments exhibit the efficiency of CD-LSR, as well as the discrimination ability of $ \ell_{2,0} $-norm to identify informative features. More importantly, the versatility of CD-LSR facilitates the applications of the $ \ell_{2,0} $-norm in more sophisticated models. Based on the competitive performance of $ \ell_{2,0} $-norm on the baseline LSR model, the satisfactory performance of its applications is reasonably expected.

Efficient Top-k Feature Selection Using Coordinate Descent Method

The Symmetric Positive Definite (SPD) matrices have received wide attention for data representation in many scientific areas. Although there are many different attempts to develop effective deep architectures for data processing on the Riemannian manifold of SPD matrices, very few solutions explicitly mine the local geometrical information in deep SPD feature representations. Given the great success of local mechanisms in Euclidean methods, we argue that it is of utmost importance to ensure the preservation of local geometric information in the SPD networks. We first analyse the convolution operator commonly used for capturing local information in Euclidean deep networks from the perspective of a higher level of abstraction afforded by category theory. Based on this analysis, we define the local information in the SPD manifold and design a multi-scale submanifold block for mining local geometry. Experiments involving multiple visual tasks validate the effectiveness of our approach.

Riemannian Local Mechanism for SPD Neural Networks

Deep Metric Learning (DML) is a group of techniques that aim to measure the similarity between objects through the neural network. Although the number of DML methods has rapidly increased in recent years,  most previous studies cannot effectively handle noisy data, which commonly exists in practical applications and often leads to serious performance deterioration. To overcome this limitation, in this paper, we build a connection between noisy samples and hard samples in the framework of self-paced learning, and propose a \underline{B}alanced \underline{S}elf-\underline{P}aced \underline{M}etric \underline{L}earning (BSPML) algorithm with a denoising multi-similarity formulation, where noisy samples are treated as extremely hard samples and adaptively excluded from the model training by  sample weighting. Especially, due to the pairwise relationship  and a new balance regularization term, the sub-problem  \emph{w.r.t.}  sample weights is a  nonconvex  quadratic function.  To efficiently solve this nonconvex  quadratic problem, we propose a doubly stochastic projection coordinate gradient algorithm. Importantly, we  theoretically prove  the convergence  not only for the doubly stochastic projection coordinate gradient algorithm, but also for our BSPML algorithm. Experimental results on several standard  data sets demonstrate that our BSPML algorithm has   better generalization ability and robustness  than  the state-of-the-art   robust DML approaches.

Denoising Multi-Similarity Formulation: A Self-paced Curriculum-Driven Approach for Robust Metric Learning

During the last decades, multi-label classification (MLC) has attracted the attention of more and more researchers due to its wide real-world applications. Many boosting methods for MLC have been proposed and achieved great successes. However, these methods only extend existing boosting frameworks to MLC and take loss functions in multi-label version to guide the iteration. These loss functions generally give a comprehensive evaluation on the label set entirety, and thus the characteristics of different labels are ignored. In this paper, we propose a multi-path AdaBoost framework specific to MLC, where each boosting path is established for distinct label and the combination of them is able to provide a maximum optimization to Hamming Loss. In each iteration, classifiers chain is taken as the base classifier to strengthen the connection between multiple AdaBoost paths and exploit the label correlation. Extensive experiments demonstrate the effectiveness of the proposed method. 

Downloads

Next from AAAI 2023

Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection

Similar lecture

Online Random Feature Forests for Learning in Varying Feature Spaces