论文检索

Reinforcement Learning · Everything Else

Deqian Kong, Dehong Xu, Minglu Zhao, Bo Pang, Jianwen Xie, Andrew Lizarraga, Yuhao Huang, Sirui Xie, Ying Nian Wu

In tasks aiming for long-term returns, planning becomes essential. We study generative modeling for planning with datasets repurposed from offline reinforcement learning. Specifically, we identify temporal consistency in the absence of step-wise rewards as one key technical challenge. We introduce the Latent Plan Transformer (LPT), a novel model that leverages a latent variable to connect a Transformer- based trajectory generator and the final return. LPT can be learned with maximum likelihood estimation on trajectory-return pairs. In learning, posterior sampling of the latent variable naturally integrates sub-trajectories to form a consistent abstrac- tion despite the finite context. At test time, the latent variable is inferred from an expected return before policy execution, realizing the idea of planning as inference. Our experiments demonstrate that LPT can discover improved decisions from sub- optimal trajectories, achieving competitive performance across several benchmarks, including Gym-Mujoco, Franka Kitchen, Maze2D, and Connect Four. It exhibits capabilities in nuanced credit assignments, trajectory stitching, and adaptation to environmental contingencies. These results validate that latent variable inference can be a strong alternative to step-wise reward prompting.

Miscellaneous Aspects of Machine Learning · Representation Learning

Connor Mclaughlin, Lili Su

Federated learning (FL) is a distributed learning framework that leverages commonalities between distributed client datasets to train a global model. Under heterogeneous clients, however, FL can fail to produce stable training results. Personalized federated learning (PFL) seeks to address this by learning individual models tailored to each client. One approach is to decompose model training into shared representation learning and personalized classifier training. Nonetheless, previous works struggle to navigate the bias-variance trade-off in classifier learning, relying solely on limited local datasets or introducing costly techniques to improve generalization.In this work, we frame representation learning as a generative modeling task, where representations are trained with a classifier based on the global feature distribution. We then propose an algorithm, pFedFDA, that efficiently generates personalized models by adapting global generative classifiers to their local feature distributions. Through extensive computer vision benchmarks, we demonstrate that our method can adjust to complex distribution shifts with significant improvements over current state-of-the-art in data-scarce settings.

Huayu Chen, Kaiwen Zheng, Hang Su, Jun Zhu

Drawing upon recent advances in language model alignment, we formulate offline Reinforcement Learning as a two-stage optimization problem: First pretraining expressive generative policies on reward-free behavior datasets, then finetuning these policies to align with task-specific annotations like Q-values. This strategy allows us to leverage abundant and diverse behavior data to enhance generalization and enable rapid adaptation to downstream tasks using minimal annotations. In particular, we introduce Efficient Diffusion Alignment (EDA) for solving continuous control problems. EDA utilizes diffusion models for behavior modeling. However, unlike previous approaches, we represent diffusion policies as the derivative of a scalar neural network with respect to action inputs. This representation is critical because it enables direct density calculation for diffusion models, making them compatible with existing LLM alignment theories. During policy fine-tuning, we extend preference-based alignment methods like Direct Preference Optimization (DPO) to align diffusion behaviors with continuous Q-functions. Our evaluation on the D4RL benchmark shows that EDA exceeds all baseline methods in overall performance. Notably, EDA maintains about 95\% of performance and still outperforms several baselines given only 1\% of Q-labelled data during fine-tuning.

Trustworthy Machine Learning

Youssef Allouah, Abdellah El Mrini, Rachid Guerraoui, Nirupam Gupta, Rafael Pinot

Federated learning (FL) is an appealing paradigm that allows a group of machines(a.k.a. clients) to learn collectively while keeping their data local. However, dueto the heterogeneity between the clients’ data distributions, the model obtainedthrough the use of FL algorithms may perform poorly on some client’s data.Personalization addresses this issue by enabling each client to have a differentmodel tailored to their own data while simultaneously benefiting from the otherclients’ data. We consider an FL setting where some clients can be adversarial, andwe derive conditions under which full collaboration fails. Specifically, we analyzethe generalization performance of an interpolated personalized FL framework in thepresence of adversarial clients, and we precisely characterize situations when fullcollaboration performs strictly worse than fine-tuned personalization. Our analysisdetermines how much we should scale down the level of collaboration, accordingto data heterogeneity and the tolerable fraction of adversarial clients. We supportour findings with empirical results on mean estimation and binary classificationproblems, considering synthetic and benchmark image classification datasets

Computer Vision

Ning-Hsu (Albert) Wang, Yu-Lun Liu

Accurately estimating depth in 360-degree imagery is crucial for virtual reality, autonomous navigation, and immersive media applications. Existing depth estimation methods designed for perspective-view imagery fail when applied to 360-degree images due to different camera projections and distortions. We propose a new depth estimation framework that uses unlabeled 360-degree data effectively. Our approach uses state-of-the-art perspective depth estimation models as teacher models to generate pseudo labels through a six-face cube projection technique, enabling efficient labeling of depth in 360-degree images. This method leverages the increasing availability of large datasets. It includes two main stages: offline mask generation for invalid regions and an online semi-supervised joint training regime. We tested our approach on benchmark datasets such as Matterport3D and Stanford2D3D, showing significant improvements in depth estimation accuracy, particularly in zero-shot scenarios. Our proposed training pipeline can enhance any 360 monocular depth estimator and demonstrate effective knowledge transfer across different camera projections and data types.

Multimodal Models

Haiwen Huang, Songyou Peng, Dan Zhang, Andreas Geiger

Names are essential to both human cognition and vision-language models. Open-vocabulary models utilize class names as text prompts to generalize to categories unseen during training. However, the precision of these names is often overlooked in existing datasets. In this paper, we address this underexplored problem by presenting a framework for "renovating" names in open-vocabulary segmentation benchmarks (RENOVATE). Our framework features a renaming model that enhances the quality of names for each visual segment. Through experiments, we demonstrate that our renovated names help train stronger open-vocabulary models with up to 15% relative improvement and significantly enhance training efficiency with improved data quality. We also show that our renovated names improve evaluation by better measuring misclassification and enabling fine-grained model analysis. We provide our code and relabelings for several popular segmentation datasets to the research community on our project page: https://andrehuang.github.io/renovate.

Multimodal Models

Yunfeng FAN, Wenchao Xu, Haozhao Wang, Song Guo

Multi-modal domain generalization (MMDG) requires that models trained on multi-modal source domains can generalize to unseen target distributions with the same modality set. Sharpness-aware minimization (SAM) is an effective technique for traditional uni-modal domain generalization (DG), however, with limited improvement in MMDG. In this paper, we identify that modality competition and discrepant uni-modal flatness are two main factors that restrict multi-modal generalization. To overcome these challenges, we propose to construct consistent flat loss regions and enhance knowledge exploitation for each modality via cross-modal knowledge transfer. Firstly, we turn to the optimization on representation-space loss landscapes instead of traditional parameter space, which allows us to build connections between modalities directly. Then, we introduce a novel method to flatten the high-loss region between minima from different modalities by interpolating mixed multi-modal representations. We implement this method by distilling and optimizing generalizable interpolated representations and assigning distinct weights for each modality considering their divergent generalization capabilities. Extensive experiments are performed on two benchmark datasets, EPIC-Kitchens and Human-Animal-Cartoon (HAC), with various modality combinations, demonstrating the effectiveness of our method under multi-source and single-source settings. Our code is open-sourced.

Zhi Wang, Li Zhang, Wenhao Wu, Yuanheng Zhu, Dongbin Zhao, Chunlin Chen

A longstanding goal of artificial general intelligence is highly capable generalists that can learn from diverse experiences and generalize to unseen tasks. The language and vision communities have seen remarkable progress toward this trend by scaling up transformer-based models trained on massive datasets, while reinforcement learning (RL) agents still suffer from poor generalization capacity under such paradigms. To tackle this challenge, we propose Meta Decision Transformer (Meta-DT), which leverages the sequential modeling ability of the transformer architecture and robust task representation learning via world model disentanglement to achieve efficient generalization in offline meta-RL. We pretrain a context-aware world model to learn a compact task representation, and inject it as a contextual condition to the causal transformer to guide task-oriented sequence generation. Then, we subtly utilize history trajectories generated by the meta-policy as a self-guided prompt to exploit the architectural inductive bias. We select the trajectory segment that yields the largest prediction error on the pretrained world model to construct the prompt, aiming to encode task-specific information complementary to the world model maximally. Notably, the proposed framework eliminates the requirement of any expert demonstration or domain knowledge at test time. Experimental results on MuJoCo and Meta-World benchmarks across various dataset types show that Meta-DT exhibits superior few and zero-shot generalization capacity compared to strong baselines while being more practical with fewer prerequisites. Our code is available at https://github.com/NJU-RL/Meta-DT.

Generative Models · Diffusion models

Zhan Zhuang, Yulong Zhang, Xuehao Wang, Jiangang Lu, Ying Wei, Yu Zhang

Large-scale diffusion models are adept at generating high-fidelity images and facilitating image editing and interpolation. However, they have limitations when tasked with generating images in dynamic, evolving domains. In this paper, we introduce Terra, a novel Time-varying low-rank adapter that offers a fine-tuning framework specifically tailored for domain flow generation. The key innovation of Terra lies in its construction of a continuous parameter manifold through a time variable, with its expressive power analyzed theoretically. This framework not only enables interpolation of image content and style but also offers a generation-based approach to address the domain shift problems in unsupervised domain adaptation and domain generalization. Specifically, Terra transforms images from the source domain to the target domain and generates interpolated domains with various styles to bridge the gap between domains and enhance the model generalization, respectively. We conduct extensive experiments on various benchmark datasets, empirically demonstrate the effectiveness of Terra. Our source code is publicly available on https://github.com/zwebzone/terra.

Optimization · Discrete and Combinatorial Optimization

Aditya Bommakanti, Harshith Vonteri, Konstantinos Skitsas, Sayan Ranu, Davide Mottin, Panagiotis Karras

The necessity to align two graphs, minimizing a structural distance metric, is prevalent in biology, chemistry, recommender systems, and social network analysis. Due to the problem’s NP-hardness, prevailing graph alignment methods follow a modular and mediated approach, solving the problem by restricting to the domain of intermediary graph representations or products like embeddings, spectra, and graph signals. Restricting the problem to this intermediate space may distort the original problem and are hence predisposed to miss high-quality solutions. In this paper, we propose an unrestricted method, FUGAL, which finds a permutation matrix that maps one graph to another by directly operating on their adjacency matrices with judicious constraint relaxation. Extensive experimentation demonstrates that FUGAL consistently surpasses state-of-the-art graph alignment methods in accuracy across all benchmark datasets without encumbering efficiency.

Yi Ma, Jianye Hao, Xiaohan Hu, YAN ZHENG, Chenjun Xiao

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its ability to learn an effective control policy that seamlessly aligns with the inherent distribution of offline data. Unfortunately, behavior regularization, a simple yet effective offline RL algorithm, tends to struggle in this regard. In this paper, we propose a new algorithm that substantially enhances behavior-regularization based on conservative policy iteration. Our key observation is that by iteratively refining the reference policy used for behavior regularization, conservative policy update guarantees gradually improvement, while also implicitly avoiding querying out-of-sample actions to prevent catastrophic learning failures. We prove that in the tabular setting this algorithm is capable of learning the optimal policy covered by the offline dataset, commonly referred to as the in-sample optimal policy. We then explore several implementation details of the algorithm when function approximations are applied. The resulting algorithm is easy to implement, requiring only a few lines of code modification to existing methods. Experimental results on the D4RL benchmark indicate that our method outperforms previous state-of-the-art baselines in most tasks, clearly demonstrate its superiority over behavior regularization.

Miscellaneous Aspects of Machine Learning · Supervised Learning

BIN HAN, Yi-Xuan Sun, Ya-Lin Zhang, Libang Zhang, Haoran Hu, Longfei Li, Jun Zhou, Guo Ye, HUIMEI HE

This paper considers the problem of learning from multiple sets of inaccurate labels, which can be easily obtained from low-cost annotators, such as rule-based annotators. Previous works typically concentrate on aggregating information from all the annotators, overlooking the significance of data refinement. This paper presents a collaborative refining approach for learning from inaccurate labels. To refine the data, we introduce the annotator agreement as an instrument, which refers to whether multiple annotators agree or disagree on the labels for a given sample. For samples where some annotators disagree, a comparative strategy is proposed to filter noise. Through theoretical analysis, the connections among multiple sets of labels, the respective models trained on them, and the true labels are uncovered to identify relatively reliable labels. For samples where all annotators agree, an aggregating strategy is designed to mitigate potential noise. Guided by theoretical bounds on loss values, a sample selection criterion is introduced and modified to be more robust against potentially problematic values. Through these two methods, all the samples are refined during training, and these refined samples are used to train a lightweight model simultaneously. Extensive experiments are conducted on benchmark and real-world datasets to demonstrate the superiority of our methods.

Shirley Wu, Kaidi Cao, Bruno Ribeiro, James Zou, Jure Leskovec

Graph data are inherently complex and heterogeneous, leading to a high natural diversity of distributional shifts. However, it remains unclear how to build machine learning architectures that generalize to the complex distributional shifts naturally occurring in the real world. Here, we develop GraphMETRO, a Graph Neural Network architecture that models natural diversity and captures complex distributional shifts. GraphMETRO employs a Mixture-of-Experts (MoE) architecture with a gating model and multiple expert models, where each expert model targets a specific distributional shift to produce a referential representation w.r.t. a reference model, and the gating model identifies shift components. Additionally, we design a novel objective that aligns the representations from different expert models to ensure reliable optimization. GraphMETRO achieves state-of-the-art results on four datasets from the GOOD benchmark, which is comprised of complex and natural real-world distribution shifts, improving by 67% and 4.2% on the WebKB and Twitch datasets. Code and data are available at https://github.com/Wuyxin/GraphMETRO.

Multimodal Models

Huilong Jin, Yingxue Zhang, Lei Shi, Shuang Zhang, Feifei Kou, Jiapeng Yang, Chuangying Zhu, Jia Luo

Due to its low storage cost and fast search speed, cross-modal retrieval based on hashing has attracted widespread attention and is widely used in real-world applications of social media search. However, most existing hashing methods are often limited by uncomprehensive feature representations and semantic associations, which greatly restricts their performance and applicability in practical applications. To deal with this challenge, in this paper, we propose an end-to-end graph attention network hashing (EGATH) for cross-modal retrieval, which can not only capture direct semantic associations between images and texts but also match semantic content between different modalities. We adopt the contrastive language image pretraining (CLIP) combined with the Transformer to improve understanding and generalization ability in semantic consistency across different data modalities. The classifier based on graph attention network is applied to obtain predicted labels to enhance cross-modal feature representation. We construct hash codes using an optimization strategy and loss function to preserve the semantic information and compactness of the hash code. Comprehensive experiments on the NUS-WIDE, MIRFlickr25K, and MS-COCO benchmark datasets show that our EGATH significantly outperforms against several state-of-the-art methods.

Computer Vision

Juelin Zhu, Shen Yan, Long Wang, zhang shengYue, Yu Liu, Maojun Zhang

We propose a new method named LoD-Loc for visual localization in the air. Unlike existing localization algorithms, LoD-Loc does not rely on complex 3D representations and can estimate the pose of an Unmanned Aerial Vehicle (UAV) using a Level-of-Detail (LoD) 3D map. LoD-Loc mainly achieves this goal by aligning the wireframe derived from the LoD projected model with that predicted by the neural network. Specifically, given a coarse pose provided by the UAV sensor, LoD-Loc hierarchically builds a cost volume for uniformly sampled pose hypotheses to describe pose probability distribution and select a pose with maximum probability. Each cost within this volume measures the degree of line alignment between projected and predicted wireframes. LoD-Loc also devises a 6-DoF pose optimization algorithm to refine the previous result with a differentiable Gaussian-Newton method. As no public dataset exists for the studied problem, we collect two datasets with map levels of LoD3.0 and LoD2.0, along with real RGB queries and ground-truth pose annotations. We benchmark our method and demonstrate that LoD-Loc achieves excellent performance, even surpassing current state-of-the-art methods that use textured 3D models for localization. The code and dataset will be made available upon publication.

Theory · Domain Adaptation and Transfer Learning

Yongzhe Jia, Xuyun Zhang, Hongsheng Hu, Kim-Kwang Raymond Choo, Lianyong Qi, Xiaolong Xu, Amin Beheshti, Wanchun Dou

Federated learning (FL) has emerged as a prominent machine learning paradigm in edge computing environments, enabling edge devices to collaboratively optimize a global model without sharing their private data. However, existing FL frameworks suffer from efficacy deterioration due to the system heterogeneity inherent in edge computing, especially in the presence of domain shifts across local data. In this paper, we propose a heterogeneous FL framework DapperFL, to enhance model performance across multiple domains. In DapperFL, we introduce a dedicated Model Fusion Pruning (MFP) module to produce personalized compact local models for clients to address the system heterogeneity challenges. The MFP module prunes local models with fused knowledge obtained from both local and remaining domains, ensuring robustness to domain shifts. Additionally, we design a Domain Adaptive Regularization (DAR) module to further improve the overall performance of DapperFL. The DAR module employs regularization generated by the pruned model, aiming to learn robust representations across domains. Furthermore, we introduce a specific aggregation algorithm for aggregating heterogeneous local models with tailored architectures and weights. We implement DapperFL on a real-world FL platform with heterogeneous clients. Experimental results on benchmark datasets with multiple domains demonstrate that DapperFL outperforms several state-of-the-art FL frameworks by up to 2.28%, while significantly achieving model volume reductions ranging from 20% to 80%. Our code is available at: https://github.com/jyzgh/DapperFL.

Robotics

Lirui Wang, Xinlei Chen, Jialiang Zhao, Kaiming He

One of the roadblocks for training generalist robotic models today is heterogeneity. Previous robot learning methods often collect data to train with one specific embodiment for one task, which is expensive and prone to overfitting. This work studies the problem of learning policy representations through heterogeneous pre-training on robot data across different embodiments and tasks at scale. We propose Heterogeneous Pre-trained Transformers (HPT), which pre-train a large, shareable trunk of a policy neural network to learn a task and embodiment agnostic shared representation. This general architecture aligns the specific proprioception and vision inputs from distinct embodiments to a short sequence of tokens and then processes such tokens to map to control robots for different tasks. Leveraging the recent large-scale multi-embodiment real-world robotic datasets as well as simulation, deployed robots, and human video datasets, we investigate pre-training policies across heterogeneity. We conduct experiments to investigate the scaling behaviors of training objectives, to the extent of 52 datasets. HPTs outperform several baselines and enhance the fine-tuned policy performance by over 20% on unseen tasks in multiple simulator benchmarks and real-world settings. See the project website (liruiw.github.io/hpt) for code and videos.

Deep Learning · Algorithms

Zun Wang, Chang Liu, Nianlong Zou, He Zhang, Xinran Wei, Lin Huang, Lijun Wu, Bin Shao

In this study, we introduce a unified neural network architecture, the Deep Equilibrium Density Functional Theory Hamiltonian (DEQH) model, which incorporates Deep Equilibrium Models (DEQs) for predicting Density Functional Theory (DFT) Hamiltonians. The DEQH model inherently captures the self-consistency nature of Hamiltonian, a critical aspect often overlooked by traditional machine learning approaches for Hamiltonian prediction. By employing DEQ within our model architecture, we circumvent the need for DFT calculations during the training phase to introduce the Hamiltonian's self-consistency, thus addressing computational bottlenecks associated with large or complex systems. We propose a versatile framework that combines DEQ with off-the-shelf machine learning models for predicting Hamiltonians. When benchmarked on the MD17 and QH9 datasets, DEQHNet, an instantiation of the DEQH framework, has demonstrated a significant improvement in prediction accuracy. Beyond a predictor, the DEQH model is a Hamiltonian solver, in the sense that it uses the fixed-point solving capability of the deep equilibrium model to iteratively solve for the Hamiltonian. Ablation studies of DEQHNet further elucidate the network's effectiveness, offering insights into the potential of DEQ-integrated networks for Hamiltonian learning. We open source our implementation at https://github.com/Zun-Wang/DEQHNet.

Miscellaneous Aspects of Machine Learning · Unsupervised and Semi-supervised Learning

Marzi Heidari, Hanping Zhang, Yuhong Guo

In recent years, semi-supervised learning (SSL) has gained significant attention due to its ability to leverage both labeled and unlabeled data to improve model performance, especially when labeled data is scarce. However, most current SSL methods rely on heuristics or predefined rules for generating pseudo-labels and leveraging unlabeled data. They are limited to exploiting loss functions and regularization methods within the standard norm. In this paper, we propose a novel Reinforcement Learning (RL) Guided SSL method, RLGSSL, that formulates SSL as a one-armed bandit problem and deploys an innovative RL loss based on weighted reward to adaptively guide the learning process of the prediction model. RLGSSL incorporates a carefully designed reward function that balances the use of labeled and unlabeled data to enhance generalization performance. A semi-supervised teacher-student framework is further deployed to increase the learning stability. We demonstrate the effectiveness of RLGSSL through extensive experiments on several benchmark datasets and show that our approach achieves consistent superior performance compared to state-of-the-art SSL methods.

Computer Vision

Yuhui Quan, Tianxiang Zheng, Hui Ji

Real-world image denoising remains a challenge task. This paper studies self-supervised image denoising, requiring only noisy images captured in a single shot. We revamping the blind-spot technique by leveraging the transformer’s capability for long-range pixel interactions, which is crucial for effectively removing noise dependence in relating pixel–a requirement for achieving great performance for the blind-spot technique. The proposed method integrates these elements with two key innovations: a directional self-attention (DSA) module using a half-plane grid for self-attention, creating a sophisticated blind-spot structure, and a Siamese architecture with mutual learning to mitigate the performance impactsfrom the restricted attention grid in DSA. Experiments on benchmark datasets demonstrate that our method outperforms existing self-supervised and clean-image-free methods. This combination of blind-spot and transformer techniques provides a natural synergy for tackling real-world image denoising challenges.