Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning最新文献_第9页

Evolving Semantic Prototype Improves Generative Zero-Shot Learning 进化语义原型改进生成零射击学习

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-12 DOI: 10.48550/arXiv.2306.06931

Shiming Chen, W. Hou, Ziming Hong, Xiaohan Ding, Yibing Song, Xinge You, Tongliang Liu, Kun Zhang

{"title":"Evolving Semantic Prototype Improves Generative Zero-Shot Learning","authors":"Shiming Chen, W. Hou, Ziming Hong, Xiaohan Ding, Yibing Song, Xinge You, Tongliang Liu, Kun Zhang","doi":"10.48550/arXiv.2306.06931","DOIUrl":"https://doi.org/10.48550/arXiv.2306.06931","url":null,"abstract":"In zero-shot learning (ZSL), generative methods synthesize class-related sample features based on predefined semantic prototypes. They advance the ZSL performance by synthesizing unseen class sample features for better training the classifier. We observe that each class's predefined semantic prototype (also referred to as semantic embedding or condition) does not accurately match its real semantic prototype. So the synthesized visual sample features do not faithfully represent the real sample features, limiting the classifier training and existing ZSL performance. In this paper, we formulate this mismatch phenomenon as the visual-semantic domain shift problem. We propose a dynamic semantic prototype evolving (DSP) method to align the empirically predefined semantic prototypes and the real prototypes for class-related feature synthesis. The alignment is learned by refining sample features and semantic prototypes in a unified framework and making the synthesized visual sample features approach real sample features. After alignment, synthesized sample features from unseen classes are closer to the real sample features and benefit DSP to improve existing generative ZSL methods by 8.5%, 8.0%, and 9.7% on the standard CUB, SUN AWA2 datasets, the significant performance improvement indicates that evolving semantic prototype explores a virgin field in ZSL.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"13 1","pages":"4611-4622"},"PeriodicalIF":0.0,"publicationDate":"2023-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80989238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Approximation Algorithms for Fair Range Clustering 公平范围聚类的近似算法

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-11 DOI: 10.48550/arXiv.2306.06778

S. S. Hotegni, S. Mahabadi, A. Vakilian

引用次数: 1

Policy Regularization with Dataset Constraint for Offline Reinforcement Learning 基于数据集约束的离线强化学习策略正则化

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-11 DOI: 10.48550/arXiv.2306.06569

Yuhang Ran, Yichen Li, Fuxiang Zhang, Zongzhang Zhang, Yang Yu

{"title":"Policy Regularization with Dataset Constraint for Offline Reinforcement Learning","authors":"Yuhang Ran, Yichen Li, Fuxiang Zhang, Zongzhang Zhang, Yang Yu","doi":"10.48550/arXiv.2306.06569","DOIUrl":"https://doi.org/10.48550/arXiv.2306.06569","url":null,"abstract":"We consider the problem of learning the best possible policy from a fixed dataset, known as offline Reinforcement Learning (RL). A common taxonomy of existing offline RL works is policy regularization, which typically constrains the learned policy by distribution or support of the behavior policy. However, distribution and support constraints are overly conservative since they both force the policy to choose similar actions as the behavior policy when considering particular states. It will limit the learned policy's performance, especially when the behavior policy is sub-optimal. In this paper, we find that regularizing the policy towards the nearest state-action pair can be more effective and thus propose Policy Regularization with Dataset Constraint (PRDC). When updating the policy in a given state, PRDC searches the entire dataset for the nearest state-action sample and then restricts the policy with the action of this sample. Unlike previous works, PRDC can guide the policy with proper behaviors from the dataset, allowing it to choose actions that do not appear in the dataset along with the given state. It is a softer constraint but still keeps enough conservatism from out-of-distribution actions. Empirical evidence and theoretical analysis show that PRDC can alleviate offline RL's fundamentally challenging value overestimation issue with a bounded performance gap. Moreover, on a set of locomotion and navigation tasks, PRDC achieves state-of-the-art performance compared with existing methods. Code is available at https://github.com/LAMDA-RL/PRDC","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"28 1","pages":"28701-28717"},"PeriodicalIF":0.0,"publicationDate":"2023-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89343386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Group Equivariant Fourier Neural Operators for Partial Differential Equations 偏微分方程的群等变傅里叶神经算子

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-09 DOI: 10.48550/arXiv.2306.05697

Jacob Helwig, Xuan Zhang, Cong Fu, Jerry Kurtin, Stephan Wojtowytsch, Shuiwang Ji

引用次数: 4

Fair yet Asymptotically Equal Collaborative Learning 公平而渐进平等的协作学习

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-09 DOI: 10.48550/arXiv.2306.05764

Xiaoqiang Lin, Xinyi Xu, See-Kiong Ng, Chuan-Sheng Foo, B. Low

{"title":"Fair yet Asymptotically Equal Collaborative Learning","authors":"Xiaoqiang Lin, Xinyi Xu, See-Kiong Ng, Chuan-Sheng Foo, B. Low","doi":"10.48550/arXiv.2306.05764","DOIUrl":"https://doi.org/10.48550/arXiv.2306.05764","url":null,"abstract":"In collaborative learning with streaming data, nodes (e.g., organizations) jointly and continuously learn a machine learning (ML) model by sharing the latest model updates computed from their latest streaming data. For the more resourceful nodes to be willing to share their model updates, they need to be fairly incentivized. This paper explores an incentive design that guarantees fairness so that nodes receive rewards commensurate to their contributions. Our approach leverages an explore-then-exploit formulation to estimate the nodes' contributions (i.e., exploration) for realizing our theoretically guaranteed fair incentives (i.e., exploitation). However, we observe a\"rich get richer\"phenomenon arising from the existing approaches to guarantee fairness and it discourages the participation of the less resourceful nodes. To remedy this, we additionally preserve asymptotic equality, i.e., less resourceful nodes achieve equal performance eventually to the more resourceful/\"rich\"nodes. We empirically demonstrate in two settings with real-world streaming data: federated online incremental learning and federated reinforcement learning, that our proposed approach outperforms existing baselines in fairness and learning performance while remaining competitive in preserving equality.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"8 1","pages":"21223-21259"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83660665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions 在深度强化学习中检测对抗方向以做出稳健决策

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-09 DOI: 10.48550/arXiv.2306.05873

Ezgi Korkmaz, Jonah Brown-Cohen

{"title":"Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions","authors":"Ezgi Korkmaz, Jonah Brown-Cohen","doi":"10.48550/arXiv.2306.05873","DOIUrl":"https://doi.org/10.48550/arXiv.2306.05873","url":null,"abstract":"Learning in MDPs with highly complex state representations is currently possible due to multiple advancements in reinforcement learning algorithm design. However, this incline in complexity, and furthermore the increase in the dimensions of the observation came at the cost of volatility that can be taken advantage of via adversarial attacks (i.e. moving along worst-case directions in the observation space). To solve this policy instability problem we propose a novel method to detect the presence of these non-robust directions via local quadratic approximation of the deep neural policy loss. Our method provides a theoretical basis for the fundamental cut-off between safe observations and adversarial observations. Furthermore, our technique is computationally efficient, and does not depend on the methods used to produce the worst-case directions. We conduct extensive experiments in the Arcade Learning Environment with several different adversarial attack techniques. Most significantly, we demonstrate the effectiveness of our approach even in the setting where non-robust directions are explicitly optimized to circumvent our proposed method.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"51 17","pages":"17534-17543"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91453101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Path Neural Networks: Expressive and Accurate Graph Neural Networks 路径神经网络:表达和准确的图神经网络

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-09 DOI: 10.48550/arXiv.2306.05955

Gaspard Michel, Giannis Nikolentzos, J. Lutzeyer, M. Vazirgiannis

{"title":"Path Neural Networks: Expressive and Accurate Graph Neural Networks","authors":"Gaspard Michel, Giannis Nikolentzos, J. Lutzeyer, M. Vazirgiannis","doi":"10.48550/arXiv.2306.05955","DOIUrl":"https://doi.org/10.48550/arXiv.2306.05955","url":null,"abstract":"Graph neural networks (GNNs) have recently become the standard approach for learning with graph-structured data. Prior work has shed light into their potential, but also their limitations. Unfortunately, it was shown that standard GNNs are limited in their expressive power. These models are no more powerful than the 1-dimensional Weisfeiler-Leman (1-WL) algorithm in terms of distinguishing non-isomorphic graphs. In this paper, we propose Path Neural Networks (PathNNs), a model that updates node representations by aggregating paths emanating from nodes. We derive three different variants of the PathNN model that aggregate single shortest paths, all shortest paths and all simple paths of length up to K. We prove that two of these variants are strictly more powerful than the 1-WL algorithm, and we experimentally validate our theoretical results. We find that PathNNs can distinguish pairs of non-isomorphic graphs that are indistinguishable by 1-WL, while our most expressive PathNN variant can even distinguish between 3-WL indistinguishable graphs. The different PathNN variants are also evaluated on graph classification and graph regression datasets, where in most cases, they outperform the baseline methods.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"5 1","pages":"24737-24755"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90073098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Differentially Private Sharpness-Aware Training 不同的私人敏锐意识训练

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-09 DOI: 10.48550/arXiv.2306.05651

Jinseong Park, Hoki Kim, Yujin Choi, Jaewook Lee

{"title":"Differentially Private Sharpness-Aware Training","authors":"Jinseong Park, Hoki Kim, Yujin Choi, Jaewook Lee","doi":"10.48550/arXiv.2306.05651","DOIUrl":"https://doi.org/10.48550/arXiv.2306.05651","url":null,"abstract":"Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from standard training, whereas understanding the geometric properties of private learning remains largely unexplored. In this paper, we investigate sharpness, a key factor in achieving better generalization, in private learning. We show that flat minima can help reduce the negative effects of per-example gradient clipping and the addition of Gaussian noise. We then verify the effectiveness of Sharpness-Aware Minimization (SAM) for seeking flat minima in private learning. However, we also discover that SAM is detrimental to the privacy budget and computational time due to its two-step optimization. Thus, we propose a new sharpness-aware training method that mitigates the privacy-optimization trade-off. Our experimental results demonstrate that the proposed method improves the performance of deep learning models with DP from both scratch and fine-tuning. Code is available at https://github.com/jinseongP/DPSAT.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"27 1","pages":"27204-27224"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83905958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Expectation-Complete Graph Representations with Homomorphisms 具有同态的期望完备图表示

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-09 DOI: 10.48550/arXiv.2306.05838

Pascal Welke, Maximilian Thiessen, Fabian Jogl, T. Gartner

引用次数: 1

Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs 量化gnn中的知识以实现可靠蒸馏到mlp

Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning Pub Date : 2023-06-09 DOI: 10.48550/arXiv.2306.05628

Lirong Wu, Haitao Lin, Yufei Huang, Stan Z. Li

{"title":"Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs","authors":"Lirong Wu, Haitao Lin, Yufei Huang, Stan Z. Li","doi":"10.48550/arXiv.2306.05628","DOIUrl":"https://doi.org/10.48550/arXiv.2306.05628","url":null,"abstract":"To bridge the gaps between topology-aware Graph Neural Networks (GNNs) and inference-efficient Multi-Layer Perceptron (MLPs), GLNN proposes to distill knowledge from a well-trained teacher GNN into a student MLP. Despite their great progress, comparatively little work has been done to explore the reliability of different knowledge points (nodes) in GNNs, especially their roles played during distillation. In this paper, we first quantify the knowledge reliability in GNN by measuring the invariance of their information entropy to noise perturbations, from which we observe that different knowledge points (1) show different distillation speeds (temporally); (2) are differentially distributed in the graph (spatially). To achieve reliable distillation, we propose an effective approach, namely Knowledge-inspired Reliable Distillation (KRD), that models the probability of each node being an informative and reliable knowledge point, based on which we sample a set of additional reliable knowledge points as supervision for training student MLPs. Extensive experiments show that KRD improves over the vanilla MLPs by 12.62% and outperforms its corresponding teacher GNNs by 2.16% averaged over 7 datasets and 3 GNN architectures.","PeriodicalId":74529,"journal":{"name":"Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning","volume":"107 1","pages":"37571-37581"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79316849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2