Discovering achievements with a hierarchical structure in procedurally generated environments presents a significant challenge. This requires an agent to possess a broad range of abilities, including generalization and long-term reasoning. Many prior methods have been built upon model-based or hierarchical approaches, with the belief that an explicit module for long-term planning would be advantageous for learning hierarchical dependencies. However, these methods demand an excessive number of environment interactions or large model sizes, limiting their practicality. In this work, we demonstrate that proximal policy optimization (PPO), a simple yet versatile model-free algorithm, outperforms previous methods when optimized with recent implementation practices. Moreover, we find that the PPO agent can predict the next achievement to be unlocked to some extent, albeit with limited confidence. Based on this observation, we introduce a novel contrastive learning method, called achievement distillation, which strengthens the agent's ability to predict the next achievement. Our method exhibits a strong capacity for discovering hierarchical achievements and shows state-of-the-art performance on the challenging Crafter environment in a sample-efficient manner while utilizing fewer model parameters.
Most dialogue systems in real world rely on predefined intents and answers for QA service, so discovering potential intents from large corpus previously is really important for building such dialogue services. Considering that most scenarios have few intents known already and most intents waiting to be discovered, we focus on semi-supervised text clustering and try to make the proposed method benefit from labeled samples for better overall clustering performance. In this paper, we propose Deep Contrastive Semi-supervised Clustering (DCSC), which aims to cluster text samples in a semi-supervise…
Enhancing Contrastive Learning for Geolocalization by Discovering Hard Negatives on Semivariograms
Professorship Big Geospatial Data Management, Technical University of Munich Germany（技术大学慕尼黑大数据地理空间管理教授职位）；University of Maine United States（缅因大学）；University of the Bundeswehr Munich Germany（联邦国防军大学慕尼黑）
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Recently, vehicle re-identification methods based on deep learning constitute remarkable achievement. However, this achievement requires large-scale and well-annotated datasets. In constructing the dataset, assigning globally available identities (Ids) to vehicles captured from a great number of cameras is labour-intensive, because it needs to consider their subtle appearance differences or viewpoint variations. In this paper, we propose camera-tracklet-aware contrastive learning (CTACL) using the multi-camera tracklet information without vehicle identity labels. The proposed CTACL divides an …
HKUST（香港科技大学）；Xi’an Jiaotong University（西安交通大学）；Microsoft Research Asia（微软亚洲研究院）；EIT（欧洲创新与技术学院）
From the intuitive notion of disentanglement, the image variations corresponding to different factors should be distinct from each other, and the disentangled representation should reflect those variations with separate dimensions. To discover the factors and learn disentangled representation, previous methods typically leverage an extra regularization term when learning to generate realistic images. However, the term usually results in a trade-off between disentanglement and generation quality. For the generative models pretrained without any disentanglement term, the generated images show se…
The aim of this paper is to demonstrate the efficacy of using Contrastive Random Walk as a curiosity method to achieve faster convergence to the optimal policy.Contrastive Random Walk defines the transition matrix of a random walk with the help of neural networks. It learns a meaningful state representation with a closed loop. The loss of Contrastive Random Walk serves as an intrinsic reward and is added to the environment reward. Our method works well in non-tabular sparse reward scenarios, in the sense that our method receives the highest reward within the same iterations compared to other m…
CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification
Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE（机器学习系，Mohamed bin Zayed人工智能大学，阿布扎赫德，阿联酋）；JD Explore Academy, Beijing, China（京东探索研究院，北京，中国）；Department of Computer Science and Technology, National University of Defense Technology, Changsha, China（计算机科学与技术系，国防科技大学，长沙，中国）；School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China（计算机科学与技术学院，哈尔滨工业大学，深圳，中国）；Department of Computer Science, University of California, Los Angeles, USA（计算机科学系，加州大学洛杉矶分校，美国）
Zhejiang University（浙江大学）；AZFT Joint Lab for Knowledge Engine（AZFT知识引擎联合实验室）；Hangzhou Innovation Center, Zhejiang University（浙江大学杭州国际科创中心）
Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs. Intuitively, the representations should be similar in the feature space with subtle input permutations, while large variations occur with different meanings. This motivates us to investigate the learning of robust textual representation in a contrastive mann…
Xi’an Jiaotong University（西安交通大学）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）；Zhejiang University（浙江大学）；Lenovo Research（联想研究院）
Novel category discovery aims at adapting models trained on known categories to novel categories. Previous works only focus on the scenario where known and novel categories are of the same granularity. In this paper, we investigate a new practical scenario called Fine-grained Category Discovery under Coarse-grained supervision (FCDC). FCDC aims at discovering fine-grained categories with only coarse-grained labeled data, which can adapt models to categories of different granularity from known ones and reduce significant labeling cost. It is also a challenging task since supervised training on …
Contrastive Training of Complex-Valued Autoencoders for Object Discovery
The Swiss AI Lab, IDSIA, USI & SUPSI（瑞士AI实验室，IDSIA，USI与SUPSI）；Center for Brain Science, Harvard University（哈佛大学脑科学中心）；AI Initiative, KAUST（阿卜杜拉国王科技大学AI计划）
Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often overlap with each other in the representation space at the beginning of the learning process, which poses a significant challenge for distance-based clustering in achieving good separation between different categories. To this end, we propose Supporting Clustering with Contrastive Learning (SCCL) -- a novel framework to leverage contrastive learning to promote better separation. We assess the performance of SCCL on shor…
This paper proposes a novel cell-based neural architecture search algorithm (NAS), which completely alleviates the expensive costs of data labeling inherited from supervised learning. Our algorithm capitalizes on the effectiveness of self-supervised learning for image representations, which is an increasingly crucial topic of computer vision. First, using only a small amount of unlabeled train data under contrastive self-supervised learning allow us to search on a more extensive search space, discovering better neural architectures without surging the computational resources. Second, we entire…
Robust Graph Contrastive Learning with Information Restoration
Department of Computer Science, Hong Kong Chu Hai College（香港 Chu Hai 学院计算机科学系）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算系）；Department of Computer Science and Engineering, Washington University in St. Louis（华盛顿大学圣路易斯分校计算机科学与工程系）
EG-ConMix: An Intrusion Detection Method based on Graph Contrastive Learning
Fujian Power Co., Ltd. Electric Power Research Institute（福建电力有限公司电力科学研究院）；State Grid Fujian Electric Power Co., Ltd.（国网福建省电力有限公司）；Institute of Cyberspace Security, Zhejiang University of Technology（浙江工业大学网络空间安全研究院）；Binjiang Cyberspace Security Institute of ZJUT（浙江工业大学滨江网络空间安全研究院）
Automated Detection of Myopic Maculopathy in MMAC 2023: Achievements in Classification, Segmentation, and Spherical Equivalent Prediction
LaTIM UMR 1101, Inserm（法国国家健康与医学研究院LaTIM UMR 1101实验室）；Univ Bretagne Occidentale（西布列塔尼大学）；Evolucare Technologies（Evolucare科技公司）；University of Electronic Science and Technology of China（电子科技大学）；College of Computer Science, Sichuan University（四川大学计算机学院）；IMT Atlantique
Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）；Barcelona Supercomputing Center（巴塞罗那超级计算中心）；Institut de Robòtica i Informàtica Industrial, CSIC-UPC（西班牙国家研究委员会-加泰罗尼亚理工大学工业机器人与信息技术研究所）
Pre-training Reinforcement Learning agents in a task-agnostic manner has shown promising results. However, previous works still struggle in learning and discovering meaningful skills in high-dimensional state-spaces, such as pixel-spaces. We approach the problem by leveraging unsupervised skill discovery and self-supervised learning of state representations. In our work, we learn a compact latent representation by making use of variational and contrastive techniques. We demonstrate that both enable RL agents to learn a set of basic navigation skills by maximizing an information theoretic objec…
Google Research, Brain Team（谷歌研究院（Brain Team））；University of Toronto（多伦多大学）
Evaluating the general abilities of intelligent agents requires complex simulation environments. Existing benchmarks typically evaluate only one narrow task per environment, requiring researchers to perform expensive training runs on many different environments. We introduce Crafter, an open world survival game with visual inputs that evaluates a wide range of general abilities within a single environment. Agents either learn from the provided reward signal or through intrinsic objectives and are evaluated by semantically meaningful achievements that can be unlocked during each episode, such a…
The optimal way for a deep reinforcement learning (DRL) agent to explore is to learn a set of skills that achieves a uniform distribution of states. Following this,we introduce DisTop, a new model that simultaneously learns diverse skills and focuses on improving rewarding skills. DisTop progressively builds a discrete topology of the environment using an unsupervised contrastive loss, a growing network and a goal-conditioned policy. Using this topology, a state-independent hierarchical policy can select where the agent has to keep discovering skills in the state space. In turn, the newly visi…
