paper-with-me

홈 › Papers

SimSiam Naming Game: A Unified Approach for Representation Learning and Emergent Communication

2024-10-29 · Nguyen Le Hoang, Tadahiro Taniguchi, Fang Tianwei, Akira Taniguchi

Emergent communication, driven by generative models, enables agents to develop a shared language for describing their individual views of the same objects through interactions. Meanwhile, self-supervised learning (SSL), particularly SimSiam, uses discriminative representation learning to make representations of augmented views of the same data point closer in the representation space. Building on the prior work of VI-SimSiam, which incorporates a generative and Bayesian perspective into the SimSiam framework via variational inference (VI) interpretation, we propose SimSiam+VAE, a unified approach for both representation learning and emergent communication. SimSiam+VAE integrates a variational autoencoder (VAE) into the predictor of the SimSiam network to enhance representation learning and capture uncertainty. Experimental results show that SimSiam+VAE outperforms both SimSiam and VI-SimSiam. We further extend this model into a communication framework called the SimSiam Naming Game (SSNG), which applies the generative and Bayesian approach based on VI to develop internal representations and emergent language, while utilizing the discriminative process of SimSiam to facilitate mutual understanding between agents. In experiments with established models, despite the dynamic alternation of agent roles during interactions, SSNG demonstrates comparable performance to the referential game and slightly outperforms the Metropolis-Hastings naming game.

📄 PDF Abstract BibTeX arXiv:2410.21803

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningSelf-Supervised LearningVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models

2022-05-24 · Tadahiro Taniguchi, Yuto Yoshida, Akira Taniguchi, Yoshinobu Hagiwara

Constructive studies on symbol emergence systems seek to investigate computational models that can better explain human language evolution, the creation of symbol systems, and the construction of internal representations…

Bayesian InferenceDeep Reinforcement LearningRepresentation Learning

How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning

2022-03-30 · Chaoning Zhang, Kang Zhang, Chenshuang Zhang, Trung X. Pham 외

To avoid collapse in self-supervised learning (SSL), a contrastive loss is widely used but often requires a large number of negative samples. Without negative samples yet achieving competitive performance, a recent work …

Contrastive LearningSelf-Supervised Learning

Recursive Metropolis-Hastings Naming Game: Symbol Emergence in a Multi-agent System based on Probabilistic Generative Models

2023-05-31 · Jun Inukai, Tadahiro Taniguchi, Akira Taniguchi, Yoshinobu Hagiwara

In the studies on symbol emergence and emergent communication in a population of agents, a computational model was employed in which agents participate in various language games. Among these, the Metropolis-Hastings nami…

Bayesian Inference

On the Optimality of Discrete Object Naming: a Kinship Case Study

2025-11-24 · Phong Le, Mees Lindeman, Raquel G. Alhama arxiv

The structure of naming systems in natural languages hinges on a trade-off between high informativeness and low complexity. Prior work capitalizes on information theory to formalize these notions; however, these studies …

Emergent LLM behaviors are observationally equivalent to data leakage

2025-05-26 · Christopher Barrie, Petter Törnberg

Ashery et al. recently argue that large language models (LLMs), when paired to play a classic "naming game," spontaneously develop linguistic conventions reminiscent of human social norms. Here, we show that their result…

Memorization