United States

The ability to continually learn over time by grasping new knowledge and remembering previously learned experiences is essential for developing an online task-oriented dialogue system (TDS). In this paper, we work on the class incremental learning scenario where the TDS is evaluated without specifying the dialogue domain. We employ contrastive distillation on the intermediate representations of dialogues to learn transferable representations that suffer less from catastrophic forgetting. Besides, we provide a dynamic update mechanism to explicitly preserve the learned experiences by only updating the parameters related to the new task while keeping other parameters fixed. Extensive experiments demonstrate that our method significantly outperforms the strong baselines.

AAAI 2023

Class Incremental Learning for Task-Oriented Dialogue System with Contrastive Distillation on Internal Representations

snlp: generation

ml: lifelong and continual learning

snlp: conversational ai/dialogue systems

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.

lightning talk

Neural network pruning is a technique of network compression by removing weights of lower importance from an optimized neural network. Often, pruned networks are compared in terms of accuracy, which is realized in terms of rewards for Deep Reinforcement Learning (DRL) networks. However, networks that estimate control actions for safety-critical tasks, must also adhere to safety requirements along with obtaining rewards. We propose a methodology to iteratively refine the weights of a pruned neural network such that we get a sparse high-performance network without significant side effects on safety.

Safety Aware Neural Pruning for Deep Reinforcement Learning

Recent studies on adversarial examples expose vulnerabilities of natural language processing (NLP) models. Existing techniques for generating adversarial examples are typically driven by deterministic heuristic rules that are agnostic to the optimal adversarial examples, a strategy that often results in attack failures. To this end, this research proposes Fraud's Bargain Attack (FBA), which utilizes a novel randomization mechanism to enlarge the searching space and enables high-quality adversarial examples to be generated with high probabilities. FBA applies the Metropolis-Hasting algorithm to enhance the selection of adversarial examples from all candidates proposed by a customized Word Manipulation Process (WMP). WMP perturbs one word at a time via insertion, removal, or substitution in a contextual-aware manner. Extensive experiments demonstrate that FBA outperforms the baselines in terms of attack success rate and imperceptibility.


Fraud’s Bargain Attacks to Textual Classifiers via Metropolis-Hasting Sampling (Student Abstract)

Feature selection (FS) is a crucial procedure in machine learning pipelines for its significant benefits in removing data redundancy and mitigating model overfitting. Since concept drift is a widespread phenomenon in streaming data and could severely affect model performance, effective FS on concept drifting data streams is imminent. However, existing state-of-the-art FS algorithms fail to adjust their selection strategy adaptively when the effective feature subset changes, making them unsuitable for drifting streams. In this paper, we propose a dynamic FS method that selects effective features on concept drifting data streams via deep reinforcement learning. Specifically, we present two novel designs: (i) a skip-mode reinforcement learning environment that shrinks action space size for high-dimensional FS tasks; (ii) a curiosity mechanism that generates intrinsic rewards to address the long-horizon exploration problem. The experiment results show that our proposed method outperforms other FS methods and can dynamically adapt to concept drifts.

Anti-drifting Feature Selection via Deep Reinforcement Learning

Keyphrase identification and classification is a Natural Language Processing and Information Retrieval task that involves extracting relevant groups of words from a given text related to the main topic. In this work, we focus on extracting keyphrases from scientific documents. We introduce TA-DA, a Topic-Aware Domain Adaptation framework for keyphrase extraction that integrates Multi-Task Learning with Adversarial Training and Domain Adaptation. Our approach improves performance over baseline models by up to 5% in the exact match of the F1-score.

TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphrase Identification and Classification (Student Abstract)

Previous research on the comprehensive negotiation strategy using deep reinforcement learning (RL) has scalability issues of not performing effectively in the large-sized domains.
We improve negotiation strategy via deep RL by considering an issue-based represented deep policy network to deal with multi-issue negotiation.
The architecture of the proposed learning agent considers the characteristics of multi-issue negotiation domains and policy-based learning.
We demonstrate that proposed method achieve equivalent or higher utility than existing negotiation agents in the large-sized domains.

Scalable Negotiating Agent Strategy via Multi-Issue Policy Network (Student Abstract)

Multi-Agent Reinforcement Learning (MARL) has been increasingly used in safety-critical applications but has no safety guarantees, especially during training. In this paper, we propose dynamic shielding, a novel decentralized MARL framework to ensure safety in both the training and deployment phases. Our framework leverages Shield, a reactive system running in parallel with the reinforcement learning algorithm, to monitor and correct agents’ behavior. In our algorithm, shields dynamically split and merge according to the environment state in order to maintain decentralization and avoid conservative behaviors while enjoying formal safety guarantees. We demonstrate the effectiveness of MARL with dynamic shielding in the mobile navigation scenario.

Tackling Safe and Efficient Multi-Agent Reinforcement Learning via Dynamic Shielding (Student Abstract)

With the boom of digital educational materials and scalable e-learning systems, the potential for realising AI-assisted personalised learning has skyrocketed. In this landscape, the automatic generation of educational questions will play a key role, enabling scalable self-assessment when a global population is manoeuvring their personalised learning journeys. We develop EduQG, a novel educational question generation model built by adapting a large language model. Our initial experiments demonstrate that EduQG can produce superior educational questions by pre-training on scientific text.

Pre-training with Scientific Text Improves Educational Question Generation

Learning to recover clear images from images having a combination of degrading factors is a challenging task. That being said, autonomous surveillance in low visibility conditions caused by high pollution/smoke, poor air quality index, low light, atmospheric scattering and haze during a blizzard, etc, becomes even more important to prevent accidents. It is thus crucial to form a solution that can not only result in a high-quality image but also which is efficient enough to be deployed for everyday use. However, the lack of proper datasets available to tackle this task limits the performance of the previous methods proposed. To this end, we generate the LowVis-AFO dataset, containing 3647 paired dark-hazy and clear images. We also introduce a new lightweight deep learning model called Low-Visibility Restoration Network (LVRNet). It outperforms previous image restoration methods with low latency, achieving a PSNR value of 25.744 and an SSIM of 0.905, hence making our approach scalable and ready for practical use.

LVRNet: Lightweight Image Restoration for Aerial Images under Low Visibility(Student Abstract)

The efficacy of topological data analysis (TDA) has been demonstrated in many different machine learning pipelines, particularly those in which structural characteristics of data are highly relevant. However, TDA's usability in large scale machine learning applications is hindered by the significant computational cost of generating persistence diagrams. In this work, a method that allows this computationally expensive process to be approximated by deep neural networks is proposed. Moreover, the method's practicality in estimating 0-dimensional persistence diagrams across a diverse range of images is shown.

Persistent Homology through Image Segmentation (Student Abstract)

This work investigates the evolution of the latent space when deep learning models are trained incrementally in non-stationary environments. We propose a methodology for visualizing the latent representations. We then show that classes that are not even targeted by the concept drift can be negatively affected, suggesting that some classes may regularize the latent space.

Downloads

Next from AAAI 2023

Safety Aware Neural Pruning for Deep Reinforcement Learning

Similar lecture

Balanced Meta Learning and Diverse Sampling for Lifelong Task-oriented Dialogue Systems