United States

The field of emergent communication aims to understand the characteristics of communication as it emerges from artificial agents solving tasks that require information exchange. Communication with discrete messages is considered a desired characteristic, for scientific and applied reasons. However,  training a multi-agent system with discrete communication is not straightforward, requiring either reinforcement learning algorithms or relaxing the discreteness requirement via a continuous approximation such as the Gumbel-softmax. Both these solutions result in poor performance compared to fully continuous communication. In this work, we propose an alternative approach to achieve discrete communication -- quantization of communicated message. Using message quantization allows us to train the model end-to-end, achieving superior performance in multiple setups. Moreover, quantization is a natural framework that runs the gamut from continuous to discrete communication. Thus,  it sets the ground for a broader view of multi-agent communication in the deep learning era. 

AAAI 2023

Emergent Quantized Communication

mas: agent communication ml: representation learning snlp: information extraction

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.

poster

This paper considers the problem of cooperative localization of multiple robots under uncertainty, communicating over a partially connected, dynamic communication network and assisted by an agile landmark. Each robot owns an IMU and a relative pose sensing suite, which can get faulty due to system or environmental uncertainty, and therefore exhibit large bias in their estimation output. For the robots to localize accurately under sensor failure and system or environmental uncertainty, a novel Distributed Learning based Decentralized Cooperative Localization (DL-DCL) algorithm is proposed that involves real-time learning of an information fusion strategy by each robot for combining pose estimates from its own sensors as well as from those of its neighboring robots, and utilizing the moving landmark's pose information as a feedback to the learning process. Convergence analysis shows that the learning process converges exponentially under certain reasonable assumptions. Simulations involving sensor failures inducing around 40-60 times increase in the nominal bias show DL-DCL's estimation performance to be approximately 40% better than the well-known covariance-based estimate fusion methods. For the evaluation of DL-DCL's implementability and fault-tolerance capability in practice, a high-fidelity simulation is carried out in Gazebo with ROS2.

Moving-Landmark assisted Distributed Learning based Decentralized Cooperative Localization (DL-DCL) with Fault Tolerance

Homography estimation is erroneous in the case of large-baseline due to the low image overlay and limited receptive field. To address it, we propose a progressive estimation strategy by converting large-baseline homography into multiple intermediate ones, cumulatively multiplying these intermediate items can reconstruct the initial homography. Meanwhile, a semi-supervised homography identity loss, which consists of two components: a supervised objective and an unsupervised objective, is introduced. The first supervised loss is acting to optimize intermediate homographies, while the second unsupervised one helps to estimate a large-baseline homography without photometric losses. To validate our method, we propose a large-scale dataset that covers regular and challenging scenes. Experiments show that our method achieves state-of-the-art performance in large-baseline scenes while keeping competitive performance in small-baseline scenes.

Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint

In this work, we propose a novel unsupervised contrastive learning framework to improve state-of-the-art sentence embeddings. First, we train a set of contrastive submodels which take multilingual round-trip translation as data augmentation. The round-trip translation naturally changes the length of the same sentence and replaces Synonyms at the same time. Then we incorporate them into a single model through knowledge distillation. Specifically, it takes an input sentence and predicts the ensemble output of all submodels via a contrastive objective. Thus we preserve nearly the same semantic expressiveness as the ensemble model without increasing the test cost. We evaluate our framework on standard semantic textual similarity (STS) tasks. Experimental results show the advantage of our framework that we achieve an average of 79.27% Spearman's correlation, a 3.02% improvement compared to the previous best results using BERT-base.

An Ensemble Distillation Framework for Sentence Embeddings with Multilingual Round-trip Translation

Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task performance. In the continuous domain, a key factor behind this success is the usage of quantized latent spaces (e.g., obtained via VQ-VAE autoencoders), which allow for dimensionality reduction and faster inference times. However, using existing pre-trained models to perform new non-trivial tasks is difficult since it requires additional fine-tuning or extensive training to elicit prompting. This paper introduces LASS as a way to perform vector-quantized Latent Autoregressive Source Separation (i.e., de-mixing an input signal into its constituent sources) without requiring additional gradient-based optimization or modifications of existing models. Our separation method relies on the Bayesian formulation in which the autoregressive models are the priors, and a discrete (non-parametric) likelihood function is constructed by performing frequency counts over latent sums of addend tokens. We test our method on images and audio with several sampling strategies (e.g., ancestral, beam search) showing competitive results with existing approaches in terms of separation quality while offering at the same time significant speedups in terms of inference time and scalability to high dimensional data.

Latent Autoregressive Source Separation

This paper focuses on contrastive learning for gait-based emotion recognition. The existing contrastive learning approaches are rarely suitable for learning skeleton-based gait representations, which suffer from limited gait diversity and inconsistent semantics. In this paper, we propose a Cross-coordinate contrastive learning framework utilizing Ambiguity samples for self-supervised Gait-based Emotion representation (CAGE). First, we propose ambiguity transform to push positive samples into ambiguous semantic space. By learning similarities between ambiguity samples and positive samples, our model can learn higher-level semantics of the gait sequences and maintain semantic diversity. Second, to encourage learning the semantic invariance, we uniquely propose cross-coordinate contrastive learning between the Cartesian coordinate and the Spherical coordinate, which brings rich supervisory signals to learn the intrinsic semantic consistency information. Exhaustive experiments show that CAGE improves existing self-supervised methods by 5%–10% accuracy, and it achieves comparable or even superior performance to supervised methods.

See Your Emotion from Gait Using Unlabeled Skeleton Data

In many real-world applications of reinforcement learning (RL), performing actions requires consuming certain types of resources that are non-replenishable in each episode. Typical applications include robotic control with limited energy and video games with consumable items. In tasks with non-replenishable resources, we observe that popular RL methods such as soft actor critic suffer from poor sample efficiency. The major reason is that, they tend to exhaust resources fast and thus the subsequent exploration is severely restricted due to the absence of resources. To address this challenge, we first formalize the aforementioned problem as a resource-restricted reinforcement learning, and then propose a novel resource-aware exploration bonus (RAEB) to make reasonable usage of resources. An appealing feature of RAEB is that, it can significantly reduce unnecessary resource-consuming trials while effectively encouraging the agent to explore unvisited states. Experiments demonstrate that the proposed RAEB significantly outperforms state-of-the-art exploration strategies in resource-restricted reinforcement learning environments, improving the sample efficiency by up to an order of magnitude.

Efficient Exploration in Resource-Restricted Reinforcement Learning

Concept bottleneck models (CBMs) (Koh et al. 2020) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions. We extend CBMs to interactive prediction settings where the model can query a human collaborator for the label to some concepts. We develop an interaction policy that, at prediction time, chooses which concepts to request a label for so as to maximally improve the final prediction. We demonstrate that a simple policy combining concept prediction uncertainty and influence of the concept on the final prediction achieves strong performance and outperforms a static approach proposed in Koh et al. (2020) as well as active feature acquisition methods proposed in the literature. We show that the interactive CBM can achieve accuracy gains of 5-10% with only 5 interactions over competitive baselines on the Caltech UCSD Birds, CheXpert and OAI datasets.

Interactive Concept Bottleneck Models

Recently, reinforcement learning (RL) have achieved impressive performance in various domains. However, most RL frameworks oversimplify the problem by assuming a static, fixed-yet-known environment and often have difficulty generalizing to real-world scenarios. In this paper, we introduce a novel challenge with a more realistic setting, Incremental Reinforcement Learning, where the search space of the Markov Decision Process (MDP) continually expands. While previous methods usually suffer from the lack of efficiency in exploring the unseen transitions, especially with increasing search space, by random sampling or depending on the learning process, we present a new exploration framework named Dual-Adaptive ε-greedy Exploration (DAE) to address the challenge of Incremental RL. Specifically, DAE employs a Meta Policy and an Explorer Network to avoid redundant computation on those sufficiently learned samples. On one hand, the Meta Policy evaluates a state’s exploration convergence and adaptively assigns the value of ε. On the other hand, the Explorer Network estimates the occurrence of each action, conditional to the given state, for nominating the least-tried one to explore. Furthermore, we release a testbed based on a synthetic environment and the Atari benchmark to validate the effectiveness of any exploration algorithms under Incremental RL. Experimental results demonstrate that the proposed framework can efficiently learn the unseen transitions in new environments, leading to a superior performance, i.e., 81.12% higher, on averagely, over eight state-of-the-art methods.

Incremental Reinforcement Learning with Dual-Adaptive ε-greedy Exploration

Ad-hoc constraints (also called generic constraints) are important for modelling Constraint Satisfaction Problems (CSPs). Many representations have been proposed to define ad-hoc constraints, such as tables, decision diagrams, binary constraint trees, automatas and context-free grammars. However, prior works mainly focus on efficient Generalized Arc Consistency (GAC) propagators of ad-hoc constraints using the representations. In this paper, we ask a more fundamental question which bears on modelling constraints in a CSP as ad-hoc constraints, how the choice of constraints and operations affect tractability. Rather than ad-hoc constraints and their GAC propagators, our focus is on their expressive power in terms of succinctness (polysize) and cost of operations/queries (polytime). We use a large set of constraint families to investigate the expressive power of 14 existing ad-hoc constraints. We show a complete map of the succinctness of the ad-hoc constraints. We also present results on the tractability of applying various operations and queries on the ad-hoc constraints. Finally, we give case studies illustrating how our results can be useful for questions in the modelling of CSPs.

The Expressive Power of Ad-hoc Constraints for Modelling CSPs

Compared to point estimates calculated by standard neural networks, Bayesian neural networks (BNN) provide probability distributions over the output predictions and model parameters, i.e., the weights. Training the weight distribution of a BNN, however, is more involved due to the intractability of the underlying Bayesian inference problem and thus, requires efficient approximations. In this paper, we propose a novel approach for BNN learning via closed-form Bayesian inference. For this purpose, the calculation of the predictive distribution of the output and the update of the weight distribution are treated as Bayesian filtering and smoothing problems, where the weights are modeled as Gaussian random variables. This allows closed-form expressions for training the network's parameters in a sequential/online fashion without gradient descent. We demonstrate our method on several UCI datasets and compare it to the state of the art.

Emergent Quantized Communication

Downloads

Next from AAAI 2023

Moving-Landmark assisted Distributed Learning based Decentralized Cooperative Localization (DL-DCL) with Fault Tolerance

Similar lecture

Fault-Tolerant Offline Multi-Agent Path Planning