United States

Stacked self-attention models receive widespread attention, due to its ability of capturing global dependency among words. However, the stacking of many layers and components generates huge parameters, leading to low parameter efficiency. In response to this issue, we propose a lightweight architecture named Continuous Self-Attention models with neural ODE networks (CSAODE). In CSAODE, continuous dynamical models (i.e., neural ODEs) are coupled with our proposed self-attention block to form a self-attention ODE solver. This solver  continuously calculates and optimizes the hidden states via only one layer of parameters to improve the  parameter efficiency. In addition, we design a novel accelerated continuous dynamical model to reduce computing costs, and integrate it in  CSAODE. Moreover, since the original self-attention ignores local information,  CSAODE makes use of N-gram convolution to encode local representations, and a fusion layer with only two trainable scalars are designed for generating sentence vectors. We perform a series of experiments on text classification, neural language inference (NLI) and text matching tasks. With fewer parameters, CSAODE outperforms state-of-the-art models on text classification tasks (e.g.,  1.3% accuracy improved on SUBJ task), and has competitive performances for NLI and text matching tasks as well.

AAAI 2021

Continuous Self-Attention Models with Neural ODE Networks

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/).


AAAI 2023

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.

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. 

We present a new synthesis framework based on the on-the-fly DFA construction for LTL over finite traces (LTLf ). Extant approaches rely heavily on the construction of the complete DFA w.r.t. the input LTLf formula, whose size can be doubly exponential to the size of the formula in the worst case. Under those approaches, the synthesis cannot be conducted unless the whole DFA is completely constructed, which is not only inefficient but also not scalable in practice. Indeed, the DFA construction is the main bottleneck of LTLf synthesis in prior work. To mitigate this challenge, we follow two steps in this paper: Firstly, we present several light-weight pre-processing techniques such that the synthesis result can be obtained even without DFA construction; Secondly, we propose to achieve the synthesis together with the on-the-fly DFA construction such that the synthesis result can be obtained before constructing the whole DFA. The on-the-fly DFA construction is implemented using the SAT-based techniques for automata generation. We compared our new approach with the traditional ones on extensive LTLf synthesis benchmarks. Experimental results showed that the pre-processing techniques have a significant advantage on the synthesis performance in terms of scalability, and the on-the-fly synthesis is able to complement extant approaches on both realizable and unrealizable cases.

On-the-Fly Synthesis for LTL over Finite Traces

Recent handwritten mathematical expression recognition (HMER) approaches treat the problem as an image-to-markup generation task where the handwritten formula is translated into a sequence (e.g. LaTeX). The encoder-decoder framework is widely used to solve this image-to-sequence problem. However, (i) for structured mathematical formula, the hierarchical structure neither in the formula nor in the markup has been explored adequately. In addition, (ii) existing image-to-markup methods could not explicitly segment mathematical symbols in the formula corresponding to each target markup token. In this paper, we address the above issues by formulating the HMER as a graph-to-graph (G2G) learning problem. Graph is more flexible and general for structure representation and learning compared with image or sequence. At the core of our method lies the embedding of input formula and output markup into graphs on primitives, with Graph Neural Networks (GNN) to explore the structural information, and a novel sub-graph attention mechanism to match primitives in the input and output graphs. We conduct extensive experiments on CROHME datasets to demonstrate the benefits of the proposed G2G model. Our method yields significant improvements over previous SOTA image-to-markup systems. Moreover, it explicitly resolves the symbol segmentation problem while still being trained end-to-end, making the whole system much more accurate and interpretable.

Graph-to-Graph: Towards Accurate and Interpretable Online Handwritten Mathematical Expression Recognition

Traditional knowledge distillation uses a two-stage training strategy to transfer knowledge from a high-capacity teacher model to a compact student model, which relies heavily on the pre-trained teacher. Recent online knowledge distillation alleviates this limitation by collaborative learning, mutual learning and online ensembling, following a one-stage end-to-end training fashion. However, collaborative learning and mutual learning fail to construct an online high-capacity teacher, whilst online ensembling ignores the collaboration among branches and its logit summation impedes the further optimisation of the ensemble teacher. In this work, we propose a novel Peer Collaborative Learning method for online knowledge distillation, which integrates online ensembling and network collaboration into a unified framework. Specifically, given a target network, we construct a multi-branch network for training, in which each branch is called a peer. We perform random augmentation multiple times on the inputs to peers and assemble feature representations outputted from peers with an additional classifier as the peer ensemble teacher. This helps to transfer knowledge from a high-capacity teacher to peers, and in turn further optimises the ensemble teacher. Meanwhile, we employ the temporal mean model of each peer as the peer mean teacher to collaboratively transfer knowledge among peers, which helps each peer to learn richer knowledge and facilitates to optimise a more stable model with better generalisation. Extensive experiments on CIFAR-10, CIFAR-100 and ImageNet show that the proposed method significantly improves the generalisation of various backbone networks and outperforms the state-of-the-art methods.

Peer Collaborative Learning for Online Knowledge Distillation

Recent theoretical analyses reveal that existing Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods need large mini-batches 
of samples (exponentially dependent on the dimension) to reduce the mean square error of gradient estimates and ensure non-asymptotic convergence guarantees
when the target distribution has a nonconvex potential function. 
In this paper, we propose a novel SG-MCMC algorithm, called Hybrid Stochastic Gradient Hamiltonian Monte Carlo (HSG-HMC) method, which needs merely one sample per iteration and possesses a simple structure with only one hyperparameter.
Such improvement leverages a hybrid stochastic gradient estimator that exploits historical stochastic gradient information to control the mean square error.
Theoretical analyses show that our method obtains the best-known overall sample complexity to achieve epsilon-accuracy in terms of the 2-Wasserstein distance for sampling from distributions with nonconvex potential functions.
Empirical studies on both simulated and real-world datasets demonstrate the advantage of our method.

A Hybrid Stochastic Gradient Hamiltonian Monte Carlo Method

An important challenge for neural networks is to learn incrementally, i.e., learn new classes without catastrophic forgetting. To overcome this problem, generative replay technique has been suggested, which can generate samples belonging to learned classes while learning new ones. However, such generative models usually suffer from increased distribution mismatch between the generated and original samples along the learning process. In this work, we propose DeepCollaboration (D-Collab), a collaborative framework of deep generative and discriminative models to solve this problem effectively. We develop a discriminative learning model to incrementally update the latent feature space for continual classification. At the same time, a generative model is introduced to achieve conditional generation using the latent feature distribution produced by the discriminative model. Importantly, the generative and discriminative models are connected through bidirectional training to enforce cycle-consistency of mappings between feature and image domains. Furthermore, a domain alignment module is used to eliminate the divergence between the feature distributions of generated images and real ones. This module together with the discriminative model can perform effective sample mining to facilitate incremental learning. Extensive experiments on several visual recognition datasets show that our system can achieve state-of-the-art performance.

DeepCollaboration: Collaborative Generative and Discriminative Models for Class Incremental Learning

Relation Extraction (RE) is to predict the relation type of two entities that are mentioned in a piece of text, e.g., a sentence or a dialogue. When the given text is long, it is challenging to identify indicative words for the relation prediction. Recent advances on RE task are from BERT-based sequence modeling and graph-based modeling of relationships among the tokens in the sequence. In this paper, we propose to construct a latent multi-view graph to capture various possible relationships among tokens. We then refine this graph to select important words for relation prediction. Finally, the representation of the refined graph and the BERT-based sequence representation are concatenated for relation extraction. Specifically, in our proposed GDPNet (Gaussian Dynamic Time Warping Pooling Net), we utilize Gaussian Graph Generator (GGG) to generate edges of the multi-view graph. The graph is then refined by Dynamic Time Warping Pooling (DTWPool). On DialogRE and TACRED, we show that GDPNet achieves the best performance on dialogue-level RE, and comparable performance with the state-of-the-arts on sentence-level RE. Our code is available at https://github.com/XueFuzhao/GDPNet.

GDPNet: Refining Latent Multi-View Graph for Relation Extraction

Peer reviewing is a central process in modern research and essential for ensuring high quality and reliability of published work.
At the same time, it is a time-consuming process and increasing interest in emerging fields often results in a high review workload, especially for senior researchers in this area.
How to cope with this problem is an open question and it is vividly discussed across all major conferences.
In this work, we propose an Argument Mining based approach for the assistance of editors, meta-reviewers, and reviewers. 
We demonstrate that the decision process in the field of scientific publications is driven by arguments and automatic argument identification is helpful in various use-cases.
One of our findings is that arguments used in the peer-review process differ from arguments in other domains making the transfer of pre-trained models difficult.
Therefore, we provide the community with a new dataset of peer-reviews from different computer science conferences with annotated arguments. 
In our extensive empirical evaluation, we show that Argument Mining can be used to efficiently extract the most relevant parts from reviews, which are paramount for the publication decision.
Also, the process remains interpretable, since the extracted arguments can be highlighted in a review without detaching them from their context.

Argument Mining Driven Analysis of Peer-Reviews

Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification. For text classification, however, existing synonym substitution based adversarial attacks are effective but not very efficient to be incorporated into practical text adversarial training. Gradient-based attacks, which are very efficient for images, are hard to be implemented for synonym substitution based text attacks due to the lexical, grammatical and semantic constraints and the discrete text input space. Thereby, we propose a fast text adversarial attack method called Fast Gradient Projection Method (FGPM) based on synonym substitution, which is about 20 times faster than existing text attack methods and could achieve similar attack performance. We then incorporate FGPM with adversarial training and propose a text defense method called Adversarial Training with FGPM enhanced by Logit pairing (ATFL). Experiments show that ATFL could significantly improve the model robustness and block the transferability of adversarial examples.

Adversarial Training with Fast Gradient Projection Method against Synonym Substitution Based Text Attacks

Many learning problems involve multiple agents optimizing different interactive functions. In these problems, the standard policy gradient algorithms fail due to the non-stationarity of the setting and the different interests of each agent. In fact, algorithms must take into account the complex dynamics of these systems to guarantee rapid convergence towards a (local) Nash equilibrium. In this paper, we propose NOHD (Newton Optimization on Helmholtz Decomposition), a Newton-like algorithm for multi-agent learning problems based on the decomposition of the dynamics of the system in its irrotational (Potential) and solenoidal (Hamiltonian) component. This method ensures quadratic convergence in purely irrotational systems and pure solenoidal systems. Furthermore, we show that NOHD is attracted to stable fixed points in general multi-agent systems and repelled by strict saddle ones. Finally, we empirically compare the NOHD's performance with that of state-of-the-art algorithms on some bimatrix games and continuous Gridworlds environment.

Newton Optimization on Helmholtz Decomposition for Continuous Games

We study a setting in which a community wishes to identify a strongly supported proposal from a large space of alternatives, in order to change the status quo. We describe a deliberation process in which agents dynamically form coalitions  around proposals that they prefer over the status quo.  We formulate conditions on the space of proposals and on the ways in which coalitions are formed that guarantee deliberation to succeed, that is, to terminate by identifying a proposal with the largest possible support. Our results provide theoretical foundations for the analysis of deliberative processes in systems for democratic deliberation support, such as, e.g., LiquidFeedback or Polis.

Downloads

Next from AAAI 2021

On-the-Fly Synthesis for LTL over Finite Traces

Similar lecture

SeDepTTSÔºö Enhancing the Naturalness via Semantic Dependency and Local Convolution for Text-to-Speech Synthesis

.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-Fly Synthesis for LTL over Finite Traces

Similar lecture

SeDepTTSÔºö Enhancing the Naturalness via Semantic Dependency and Local Convolution for Text-to-Speech Synthesis

Downloads