ICML 2023 论文列表

The goal of this paper is open-vocabulary object detection (OVOD) — building a model that can detect objects beyond the set of categories seen at training, thus enabling the user to specify categories of interest at inference without the need for model retraining. We adopt a standard two- stage object detector architecture, and explore three ways for specifying novel categories: via language descriptions, via image exemplars, or via a combination of the two. We make three contributions: first, we prompt a large language model (LLM) to generate informative language descriptions for object classes, and construct powerful text-based classifiers; second, we employ a visual aggregator on image exemplars that can ingest any number of images as input, forming vision-based classifiers; and third, we provide a simple method to fuse information from language descriptions and image exemplars, yield- ing a multi-modal classifier. When evaluating on the challenging LVIS open-vocabulary bench- mark we demonstrate that: (i) our text-based classifiers outperform all previous OVOD works; (ii) our vision-based classifiers perform as well as text-based classifiers in prior work; (iii) using multi-modal classifiers perform better than either modality alone; and finally, (iv) our text-based and multi-modal classifiers yield better performance than a fully-supervised detector.

The phenomenon of $\textit{bias amplification}$ occurs when models amplify training set biases at test time. Existing metrics measure bias amplification with respect to single annotated attributes (e.g., $\texttt{computer}$). However, large-scale datasets typically consist of instances with multiple attribute annotations (e.g., $\{\texttt{computer}, \texttt{keyboard}\}$). We demonstrate models can learn to exploit correlations with respect to multiple attributes, which are not accounted for by current metrics. Moreover, we show that current metrics can give the erroneous impression that little to no bias amplification has occurred as they aggregate positive and negative bias scores. Further, these metrics lack an ideal value, making them difficult to interpret. To address these shortcomings, we propose a new metric: $\textit{Multi-Attribute Bias Amplification}$. We validate our metric's utility through a bias amplification analysis on the COCO, imSitu, and CelebA datasets. Finally, we benchmark bias mitigation methods using our proposed metric, suggesting possible avenues for future bias mitigation efforts.

In this paper, we propose an adaptive entropy-regularization framework (ADER) for multi-agent reinforcement learning (RL) to learn the adequate amount of exploration of each agent for entropy-based exploration. In order to derive a metric for the proper level of exploration entropy for each agent, we disentangle the soft value function into two types: one for pure return and the other for entropy. By applying multi-agent value factorization to the disentangled value function of pure return, we obtain a metric to determine the relevant level of exploration entropy for each agent, given by the partial derivative of the pure-return value function with respect to (w.r.t.) the policy entropy of each agent. Based on this metric, we propose the ADER algorithm based on maximum entropy RL, which controls the necessary level of exploration across agents over time by learning the proper target entropy for each agent. Experimental results show that the proposed scheme significantly outperforms current state-of-the-art multi-agent RL algorithms.

In order for agents in multi-agent systems (MAS) to be safe, they need to take into account the risks posed by the actions of other agents. However, the dominant paradigm in game theory (GT) assumes that agents are not affected by risk from other agents and only strive to maximise their expected utility. For example, in hybrid human-AI driving systems, it is necessary to limit large deviations in reward resulting from car crashes. Although there are equilibrium concepts in game theory that take into account risk aversion, they either assume that agents are risk-neutral with respect to the uncertainty caused by the actions of other agents, or they are not guaranteed to exist. We introduce a new GT-based Risk-Averse Equilibrium (RAE) that always produces a solution that minimises the potential variance in reward accounting for the strategy of other agents. Theoretically and empirically, we show RAE shares many properties with a Nash Equilibrium (NE), establishing convergence properties and generalising to risk-dominant NE in certain cases. To tackle large-scale problems, we extend RAE to the PSRO multi-agent reinforcement learning (MARL) framework. We empirically demonstrate the minimum reward variance benefits of RAE in matrix games with high-risk outcomes. Results on MARL experiments show RAE generalises to risk-dominant NE in a trust dilemma game and that it reduces instances of crashing by 7x in an autonomous driving setting versus the best performing baseline.

Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments. However, mitigating these correlations during pre-training for large-scale models can be costly and impractical, particularly for those without access to high-performance computing resources. This paper proposes a novel approach to address spurious correlations during fine-tuning for a given domain of interest. With a focus on multi-modal models (e.g., CLIP), the proposed method leverages different modalities in these models to detect and explicitly set apart spurious attributes from the affected class, achieved through a multi-modal contrastive loss function that expresses spurious relationships through language. Our experimental results and in-depth visualizations on CLIP show that such an intervention can effectively i) improve the model's accuracy when spurious attributes are not present, and ii) directs the model's activation maps towards the actual class rather than the spurious attribute when present. In particular, on the Waterbirds dataset, our algorithm achieved a worst-group accuracy 23% higher than ERM on CLIP with a ResNet-50 backbone, and 32% higher on CLIP with a ViT backbone, while maintaining the same average accuracy as ERM.

Deep ensembles (DE) have been successful in improving model performance by learning diverse members via the stochasticity of random initialization. While recent works have attempted to promote further diversity in DE via hyperparameters or regularizing loss functions, these methods primarily still rely on a stochastic approach to explore the hypothesis space. In this work, we present Multi-Symmetry Ensembles (MSE), a framework for constructing diverse ensembles by capturing the multiplicity of hypotheses along symmetry axes, which explore the hypothesis space beyond stochastic perturbations of model weights and hyperparameters. We leverage recent advances in contrastive representation learning to create models that separately capture opposing hypotheses of invariant and equivariant functional classes and present a simple ensembling approach to efficiently combine appropriate hypotheses for a given task. We show that MSE effectively captures the multiplicity of conflicting hypotheses that is often required in large, diverse datasets like ImageNet. As a result of their inherent diversity, MSE improves classification performance, uncertainty quantification, and generalization across a series of transfer tasks. Our code is available at https://github.com/clott3/multi-sym-ensem

Multi-task learning has the potential to improve generalization by maximizing positive transfer between tasks while reducing task interference. Fully achieving this potential is hindered by manually designed architectures that remain static throughout training. On the contrary, learning in the brain occurs through structural changes that are in tandem with changes in synaptic strength. Thus, we propose *Multi-Task Structural Learning (MTSL)* that simultaneously learns the multi-task architecture and its parameters. MTSL begins with an identical single-task network for each task and alternates between a task-learning phase and a structural-learning phase. In the task learning phase, each network specializes in the corresponding task. In each of the structural learning phases, starting from the earliest layer, locally similar task layers first transfer their knowledge to a newly created group layer before being removed. MTSL then uses the group layer in place of the corresponding removed task layers and moves on to the next layers. Our empirical results show that MTSL achieves competitive generalization with various baselines and improves robustness to out-of-distribution data.

A large body of the "Inverse Reinforcement Learning" (IRL) literature focuses on recovering the reward function from a set of demonstrations of an expert agent who acts optimally or noisily optimally. Nevertheless, some recent works move away from the optimality assumption to study the "Learning from a Learner (LfL)" problem, where the challenge is inferring the reward function of a learning agent from a sequence of demonstrations produced by progressively improving policies. In this work, we take one of the initial steps in addressing the multi-agent version of this problem and propose a new algorithm, MA-LfL (Multiagent Learning from a Learner). Unlike the state-of-the-art literature, which recovers the reward functions from trajectories produced by agents in some equilibrium, we study the problem of inferring the reward functions of interacting agents in a general sum stochastic game without assuming any equilibrium state. The MA-LfL algorithm is rigorously built on a theoretical result that ensures its validity in the case of agents learning according to a multi-agent soft policy iteration scheme. We empirically test MA-LfL and we observe high positive correlation between the recovered reward functions and the ground truth.

Competitions for shareable and limited resources have long been studied with strategic agents. In reality, agents often have to learn and maximize the rewards of the resources at the same time. To design an individualized competing policy, we model the competition between agents in a novel multi-player multi-armed bandit (MPMAB) setting where players are selfish and aim to maximize their own rewards. In addition, when several players pull the same arm, we assume that these players averagely share the arms' rewards by expectation. Under this setting, we first analyze the Nash equilibrium when arms' rewards are known. Subsequently, we propose a novel Selfish MPMAB with Averaging Allocation (SMAA) approach based on the equilibrium. We theoretically demonstrate that SMAA could achieve a good regret guarantee for each player when all players follow the algorithm. Additionally, we establish that no single selfish player can significantly increase their rewards through deviation, nor can they detrimentally affect other players' rewards without incurring substantial losses for themselves. We finally validate the effectiveness of the method in extensive synthetic experiments.

Stackelberg equilibria arise naturally in a range of popular learning problems, such as in security games or indirect mechanism design, and have received increasing attention in the reinforcement learning literature. We present a general framework for implementing Stackelberg equilibria search as a multi-agent RL problem, allowing a wide range of algorithmic design choices. We discuss how previous approaches can be seen as specific instantiations of this framework. As a key insight, we note that the design space allows for approaches not previously seen in the literature, for instance by leveraging multitask and meta-RL techniques for follower convergence. We propose one such approach using contextual policies, and evaluate it experimentally on both standard and novel benchmark domains, showing greatly improved sample efficiency compared to previous approaches. Finally, we explore the effect of adopting algorithm designs outside the borders of our framework.

Accelerated magnetic resonance (MR) imaging attempts to reduce acquisition time by collecting data below the Nyquist rate. As an ill-posed inverse problem, many plausible solutions exist, yet the majority of deep learning approaches generate only a single solution. We instead focus on sampling from the posterior distribution, which provides more comprehensive information for downstream inference tasks. To do this, we design a novel conditional normalizing flow (CNF) that infers the signal component in the measurement operator's nullspace, which is later combined with measured data to form complete images. Using fastMRI brain and knee data, we demonstrate fast inference and accuracy that surpasses recent posterior sampling techniques for MRI. Code is available at https://github.com/jwen307/mri_cnf

Crowdsourcing has emerged as an effective platform for labeling large amounts of data in a cost- and time-efficient manner. Most previous work has focused on designing an efficient algorithm to recover only the ground-truth labels of the data. In this paper, we consider multi-choice crowdsourcing tasks with the goal of recovering not only the ground truth, but also the most confusing answer and the confusion probability. The most confusing answer provides useful information about the task by revealing the most plausible answer other than the ground truth and how plausible it is. To theoretically analyze such scenarios, we propose a model in which there are the top two plausible answers for each task, distinguished from the rest of the choices. Task difficulty is quantified by the probability of confusion between the top two, and worker reliability is quantified by the probability of giving an answer among the top two. Under this model, we propose a two-stage inference algorithm to infer both the top two answers and the confusion probability. We show that our algorithm achieves the minimax optimal convergence rate. We conduct both synthetic and real data experiments and demonstrate that our algorithm outperforms other recent algorithms. We also show the applicability of our algorithms in inferring the difficulty of tasks and in training neural networks with top-two soft labels.

Sparse reward remains a valuable and challenging problem in multi-agent reinforcement learning (MARL). This paper addresses this issue from a new perspective, i.e., lazy agents. We empirically illustrate how lazy agents damage learning from both exploration and exploitation. Then, we propose a novel MARL framework called Lazy Agents Avoidance through Influencing External States (LAIES). Firstly, we examine the causes and types of lazy agents in MARL using a causal graph of the interaction between agents and their environment. Then, we mathematically define the concept of fully lazy agents and teams by calculating the causal effect of their actions on external states using the do-calculus process. Based on definitions, we provide two intrinsic rewards to motivate agents, i.e., individual diligence intrinsic motivation (IDI) and collaborative diligence intrinsic motivation (CDI). IDI and CDI employ counterfactual reasoning based on the external states transition model (ESTM) we developed. Empirical results demonstrate that our proposed method achieves state-of-the-art performance on various tasks, including the sparse-reward version of StarCraft multi-agent challenge (SMAC) and Google Research Football (GRF). Our code is open-source and available at https://github.com/liuboyin/LAIES.

We investigate the problem of best arm identification in Multi-Agent Multi-Armed Bandits (MAMABs) where the rewards are defined through a factor graph. The objective is to find an optimal global action with a prescribed level of confidence and minimal sample complexity. We derive a tight instance-specific lower bound of the sample complexity and characterize the corresponding optimal sampling strategy. Unfortunately, this bound is obtained by solving a combinatorial optimization problem with a number of variables and constraints exponentially growing with the number of agents. We leverage Mean Field (MF) techniques to obtain, in a computationally efficient manner, an approximation of the lower bound. The approximation scales at most as $\rho K^d$ (where $\rho$, $K$, and $d$ denote the number of factors in the graph, the number of possible actions per agent, and the maximal degree of the factor graph). We devise MF-TaS (Mean-Field-Track-and-Stop), an algorithm whose sample complexity provably matches our approximated lower bound. We illustrate the performance of MF-TaS numerically using both synthetic and real-world experiments (e.g., to solve the antenna tilt optimization problem in radio communication networks).

We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations. This dataset is collected from a variety of biology experiments, and includes triplets of interacting mice (4.7 million frames video+pose tracking data, 10 million frames pose only), symbiotic beetle-ant interactions (10 million frames video data), and groups of interacting flies (4.4 million frames of pose tracking data). Accompanying these data, we introduce a panel of real-life downstream analysis tasks to assess the quality of learned representations by evaluating how well they preserve information about the experimental conditions (e.g. strain, time of day, optogenetic stimulation) and animal behavior. We test multiple state-of-the-art self-supervised video and trajectory representation learning methods to demonstrate the use of our benchmark, revealing that methods developed using human action datasets do not fully translate to animal datasets. We hope that our benchmark and dataset encourage a broader exploration of behavior representation learning methods across species and settings.

We study provable multi-agent reinforcement learning (MARL) in the general framework of partially observable stochastic games (POSGs). To circumvent the known hardness results and the use of computationally intractable oracles, we propose to leverage the potential *information-sharing* among agents, a standard practice in empirical MARL and a common model for multi-agent control systems with communications. We first establish several computation complexity results to justify the necessity of information-sharing, as well as the observability assumption that has enabled quasi-efficient single-agent RL with partial observations, for computational efficiency in solving POSGs. We then propose to further *approximate* the shared common information to construct an approximate model of the POSG, in which planning an approximate equilibrium (in terms of solving the original POSG) can be quasi-efficient, i.e., of quasi-polynomial-time, under the aforementioned assumptions. Furthermore, we develop a partially observable MARL algorithm that is both statistically and computationally quasi-efficient. We hope our study can open up the possibilities of leveraging and even designing different *information structures*, for developing both sample- and computation-efficient partially observable MARL.

Stochastic partial observability poses a major challenge for decentralized coordination in multi-agent reinforcement learning but is largely neglected in state-of-the-art research due to a strong focus on state-based centralized training for decentralized execution (CTDE) and benchmarks that lack sufficient stochasticity like StarCraft Multi-Agent Challenge (SMAC). In this paper, we propose Attention-based Embeddings of Recurrence In multi-Agent Learning (AERIAL) to approximate value functions under stochastic partial observability. AERIAL replaces the true state with a learned representation of multi-agent recurrence, considering more accurate information about decentralized agent decisions than state-based CTDE. We then introduce MessySMAC, a modified version of SMAC with stochastic observations and higher variance in initial states, to provide a more general and configurable benchmark regarding stochastic partial observability. We evaluate AERIAL in Dec-Tiger as well as in a variety of SMAC and MessySMAC maps, and compare the results with state-based CTDE. Furthermore, we evaluate the robustness of AERIAL and state-based CTDE against various stochasticity configurations in MessySMAC.

Learning agent behaviors from observational data has shown to improve our understanding of their decision-making processes, advancing our ability to explain their interactions with the environment and other agents. While multiple learning techniques have been proposed in the literature, there is one particular setting that has not been explored yet: multi agent systems where agent identities remain anonymous. For instance, in financial markets labeled data that identifies market participant strategies is typically proprietary, and only the anonymous state-action pairs that result from the interaction of multiple market participants are publicly available. As a result, sequences of agent actions are not observable, restricting the applicability of existing work. In this paper, we propose a Policy Clustering algorithm, called K-SHAP, that learns to group anonymous state-action pairs according to the agent policies. We frame the problem as an Imitation Learning (IL) task, and we learn a world-policy able to mimic all the agent behaviors upon different environmental states. We leverage the world-policy to explain each anonymous observation through an additive feature attribution method called SHAP (SHapley Additive exPlanations). Finally, by clustering the explanations we show that we are able to identify different agent policies and group observations accordingly. We evaluate our approach on simulated synthetic market data and a real-world financial dataset. We show that our proposal significantly and consistently outperforms the existing methods, identifying different agent strategies.