ICML 2022 Papers

Offline reinforcement learning (RL) can learn control policies from static datasets but, like standard RL methods, it requires reward annotations for every transition. In many cases, labeling large datasets with rewards may be costly, especially if those rewards must be provided by human labelers, while collecting diverse unlabeled data might be comparatively inexpensive. How can we best leverage such unlabeled data in offline RL? One natural solution is to learn a reward function from the labeled data and use it to label the unlabeled data. In this paper, we find that, perhaps surprisingly, a much simpler method that simply applies zero rewards to unlabeled data leads to effective data sharing both in theory and in practice, without learning any reward model at all. While this approach might seem strange (and incorrect) at first, we provide extensive theoretical and empirical analysis that illustrates how it trades off reward bias, sample complexity and distributional shift, often leading to good results. We characterize conditions under which this simple strategy is effective, and further show that extending it with a simple reweighting approach can further alleviate the bias introduced by using incorrect reward labels. Our empirical evaluation confirms these findings in simulated robotic locomotion, navigation, and manipulation settings.

Although traditional optimization methods focus on finding a single optimal solution, most objective functions in modern machine learning problems, especially those in deep learning, often have multiple or infinite number of optimal points. Therefore, it is useful to consider the problem of finding a set of diverse points in the optimum set of an objective function. In this work, we frame this problem as a bi-level optimization problem of maximizing a diversity score inside the optimum set of the main loss function, and solve it with a simple population gradient descent framework that iteratively updates the points to maximize the diversity score in a fashion that does not hurt the optimization of the main loss. We demonstrate that our method can efficiently generate diverse solutions on multiple applications, e.g. text-to-image generation, text-to-mesh generation, molecular conformation generation and ensemble neural network training.

Spectral Graph Neural Network is a kind of Graph Neural Network (GNN) based on graph signal filters. Some models able to learn arbitrary spectral filters have emerged recently. However, few works analyze the expressive power of spectral GNNs. This paper studies spectral GNNs’ expressive power theoretically. We first prove that even spectral GNNs without nonlinearity can produce arbitrary graph signals and give two conditions for reaching universality. They are: 1) no multiple eigenvalues of graph Laplacian, and 2) no missing frequency components in node features. We also establish a connection between the expressive power of spectral GNNs and Graph Isomorphism (GI) testing, the latter of which is often used to characterize spatial GNNs’ expressive power. Moreover, we study the difference in empirical performance among different spectral GNNs with the same expressive power from an optimization perspective, and motivate the use of an orthogonal basis whose weight function corresponds to the graph signal density in the spectrum. Inspired by the analysis, we propose JacobiConv, which uses Jacobi basis due to its orthogonality and flexibility to adapt to a wide range of weight functions. JacobiConv deserts nonlinearity while outperforming all baselines on both synthetic and real-world datasets.

Devising domain- and model-agnostic evaluation metrics for generative models is an important and as yet unresolved problem. Most existing metrics, which were tailored solely to the image synthesis setup, exhibit a limited capacity for diagnosing the different modes of failure of generative models across broader application domains. In this paper, we introduce a 3-dimensional evaluation metric, ($\alpha$-Precision, $\beta$-Recall, Authenticity), that characterizes the fidelity, diversity and generalization performance of any generative model in a domain-agnostic fashion. Our metric unifies statistical divergence measures with precision-recall analysis, enabling sample- and distribution-level diagnoses of model fidelity and diversity. We introduce generalization as an additional, independent dimension (to the fidelity-diversity trade-off) that quantifies the extent to which a model copies training data{—}a crucial performance indicator when modeling sensitive data with requirements on privacy. The three metric components correspond to (interpretable) probabilistic quantities, and are estimated via sample-level binary classification. The sample-level nature of our metric inspires a novel use case which we call model auditing, wherein we judge the quality of individual samples generated by a (black-box) model, discarding low-quality samples and hence improving the overall model performance in a post-hoc manner.

The effectiveness of knowledge graph embedding (KGE) largely depends on the ability to model intrinsic relation patterns and mapping properties. However, existing approaches can only capture some of them with insufficient modeling capacity. In this work, we propose a more powerful KGE framework named HousE, which involves a novel parameterization based on two kinds of Householder transformations: (1) Householder rotations to achieve superior capacity of modeling relation patterns; (2) Householder projections to handle sophisticated relation mapping properties. Theoretically, HousE is capable of modeling crucial relation patterns and mapping properties simultaneously. Besides, HousE is a generalization of existing rotation-based models while extending the rotations to high-dimensional spaces. Empirically, HousE achieves new state-of-the-art performance on five benchmark datasets. Our code is available at https://github.com/anrep/HousE.

In a partially observable Markov decision process (POMDP), an agent typically uses a representation of the past to approximate the underlying MDP. We propose to utilize a frozen Pretrained Language Transformer (PLT) for history representation and compression to improve sample efficiency. To avoid training of the Transformer, we introduce FrozenHopfield, which automatically associates observations with pretrained token embeddings. To form these associations, a modern Hopfield network stores these token embeddings, which are retrieved by queries that are obtained by a random but fixed projection of observations. Our new method, HELM, enables actor-critic network architectures that contain a pretrained language Transformer for history representation as a memory module. Since a representation of the past need not be learned, HELM is much more sample efficient than competitors. On Minigrid and Procgen environments HELM achieves new state-of-the-art results. Our code is available at https://github.com/ml-jku/helm.

We introduce the Lossy Implicit Network Activation Coding (LINAC) defence, an input transformation which successfully hinders several common adversarial attacks on CIFAR-10 classifiers for perturbations up to 8/255 in Linf norm and 0.5 in L2 norm. Implicit neural representations are used to approximately encode pixel colour intensities in 2D images such that classifiers trained on transformed data appear to have robustness to small perturbations without adversarial training or large drops in performance. The seed of the random number generator used to initialise and train the implicit neural representation turns out to be necessary information for stronger generic attacks, suggesting its role as a private key. We devise a Parametric Bypass Approximation (PBA) attack strategy for key-based defences, which successfully invalidates an existing method in this category. Interestingly, our LINAC defence also hinders some transfer and adaptive attacks, including our novel PBA strategy. Our results emphasise the importance of a broad range of customised attacks despite apparent robustness according to standard evaluations.

Stochastic gradient descent (SGD) is the workhorse in modern machine learning and data-driven optimization. Despite its popularity, existing theoretical guarantees for SGD are mainly derived in expectation and for convex learning problems. High probability guarantees of nonconvex SGD are scarce, and typically rely on “light-tail” noise assumptions and study the optimization and generalization performance separately. In this paper, we develop high probability bounds for nonconvex SGD with a joint perspective of optimization and generalization performance. Instead of the light tail assumption, we consider the gradient noise following a heavy-tailed sub-Weibull distribution, a novel class generalizing the sub-Gaussian and sub-Exponential families to potentially heavier-tailed distributions. Under these complicated settings, we first present high probability bounds with best-known rates in general nonconvex learning, then move to nonconvex learning with a gradient dominance curvature condition, for which we improve the learning guarantees to fast rates. We further obtain sharper learning guarantees by considering a mild Bernstein-type noise condition. Our analysis also reveals the effect of trade-offs between the optimization and generalization performance under different conditions. In the last, we show that gradient clipping can be employed to remove the bounded gradient-type assumptions. Additionally, in this case, the stepsize of SGD is completely oblivious to the knowledge of smoothness.

Nesterov’s Accelerated Gradient (NAG) for optimization has better performance than its continuous time limit (noiseless kinetic Langevin) when a finite step-size is employed (Shi et al., 2021). This work explores the sampling counterpart of this phenonemon and proposes a diffusion process, whose discretizations can yield accelerated gradient-based MCMC methods. More precisely, we reformulate the optimizer of NAG for strongly convex functions (NAG-SC) as a Hessian-Free High-Resolution ODE, change its high-resolution coefficient to a hyperparameter, inject appropriate noise, and discretize the resulting diffusion process. The acceleration effect of the new hyperparameter is quantified and it is not an artificial one created by time-rescaling. Instead, acceleration beyond underdamped Langevin in $W_2$ distance is quantitatively established for log-strongly-concave-and-smooth targets, at both the continuous dynamics level and the discrete algorithm level. Empirical experiments in both log-strongly-concave and multi-modal cases also numerically demonstrate this acceleration.

Kernel mean embedding is a useful tool to compare probability measures. Despite its usefulness, kernel mean embedding considers infinite-dimensional features, which are challenging to handle in the context of differentially private data generation. A recent work, DP-MERF (Harder et al., 2021), proposes to approximate the kernel mean embedding of data distribution using finite-dimensional random features, which yields an analytically tractable sensitivity of approximate kernel mean embedding. However, the required number of random features in DP-MERF is excessively high, often ten thousand to a hundred thousand, which worsens the sensitivity of the approximate kernel mean embedding. To improve the sensitivity, we propose to replace random features with Hermite polynomial features. Unlike the random features, the Hermite polynomial features are ordered, where the features at the low orders contain more information on the distribution than those at the high orders. Hence, a relatively low order of Hermite polynomial features can more accurately approximate the mean embedding of the data distribution compared to a significantly higher number of random features. As a result, the Hermite polynomial features help us to improve the privacy-accuracy trade-off compared to DP-MERF, as demonstrated on several heterogeneous tabular datasets, as well as several image benchmark datasets.

We explore algorithms and limitations for sparse optimization problems such as sparse linear regression and robust linear regression. The goal of the sparse linear regression problem is to identify a small number of key features, while the goal of the robust linear regression problem is to identify a small number of erroneous measurements. Specifically, the sparse linear regression problem seeks a $k$-sparse vector $x\in\mathbb{R}^d$ to minimize $\|Ax-b\|_2$, given an input matrix $A\in\mathbb{R}^{n\times d}$ and a target vector $b\in\mathbb{R}^n$, while the robust linear regression problem seeks a set $S$ that ignores at most $k$ rows and a vector $x$ to minimize $\|(Ax-b)_S\|_2$. We first show bicriteria, NP-hardness of approximation for robust regression building on the work of \cite{ODonnellWZ15} which implies a similar result for sparse regression. We further show fine-grained hardness of robust regression through a reduction from the minimum-weight $k$-clique conjecture. On the positive side, we give an algorithm for robust regression that achieves arbitrarily accurate additive error and uses runtime that closely matches the lower bound from the fine-grained hardness result, as well as an algorithm for sparse regression with similar runtime. Both our upper and lower bounds rely on a general reduction from robust linear regression to sparse regression that we introduce. Our algorithms, inspired by the 3SUM problem, use approximate nearest neighbor data structures and may be of independent interest for solving sparse optimization problems. For instance, we demonstrate that our techniques can also be used for the well-studied sparse PCA problem.

We propose Guided-TTS, a high-quality text-to-speech (TTS) model that does not require any transcript of target speaker using classifier guidance. Guided-TTS combines an unconditional diffusion probabilistic model with a separately trained phoneme classifier for classifier guidance. Our unconditional diffusion model learns to generate speech without any context from untranscribed speech data. For TTS synthesis, we guide the generative process of the diffusion model with a phoneme classifier trained on a large-scale speech recognition dataset. We present a norm-based scaling method that reduces the pronunciation errors of classifier guidance in Guided-TTS. We show that Guided-TTS achieves a performance comparable to that of the state-of-the-art TTS model, Grad-TTS, without any transcript for LJSpeech. We further demonstrate that Guided-TTS performs well on diverse datasets including a long-form untranscribed dataset.

Myopic exploration policies such as epsilon-greedy, softmax, or Gaussian noise fail to explore efficiently in some reinforcement learning tasks and yet, they perform well in many others. In fact, in practice, they are often selected as the top choices, due to their simplicity. But, for what tasks do such policies succeed? Can we give theoretical guarantees for their favorable performance? These crucial questions have been scarcely investigated, despite the prominent practical importance of these policies. This paper presents a theoretical analysis of such policies and provides the first regret and sample-complexity bounds for reinforcement learning with myopic exploration. Our results apply to value-function-based algorithms in episodic MDPs with bounded Bellman Eluder dimension. We propose a new complexity measure called myopic exploration gap, denoted by alpha, that captures a structural property of the MDP, the exploration policy and the given value function class. We show that the sample-complexity of myopic exploration scales quadratically with the inverse of this quantity, 1 / alpha^2. We further demonstrate through concrete examples that myopic exploration gap is indeed favorable in several tasks where myopic exploration succeeds, due to the corresponding dynamics and reward structure.

We develop a new approach, named Greedy when Sure and Conservative when Uncertain (GSCU), to competing online against unknown and nonstationary opponents. GSCU improves in four aspects: 1) introduces a novel way of learning opponent policy embeddings offline; 2) trains offline a single best response (conditional additionally on our opponent policy embedding) instead of a finite set of separate best responses against any opponent; 3) computes online a posterior of the current opponent policy embedding, without making the discrete and ineffective decision which type the current opponent belongs to; and 4) selects online between a real-time greedy policy and a fixed conservative policy via an adversarial bandit algorithm, gaining a theoretically better regret than adhering to either. Experimental studies on popular benchmarks demonstrate GSCU’s superiority over the state-of-the-art methods. The code is available online at \url{https://github.com/YeTianJHU/GSCU}.

Due to the representation limitation of the joint Q value function, multi-agent reinforcement learning methods with linear value decomposition (LVD) or monotonic value decomposition (MVD) suffer from relative overgeneralization. As a result, they can not ensure optimal consistency (i.e., the correspondence between individual greedy actions and the best team performance). In this paper, we derive the expression of the joint Q value function of LVD and MVD. According to the expression, we draw a transition diagram, where each self-transition node (STN) is a possible convergence. To ensure the optimal consistency, the optimal node is required to be the unique STN. Therefore, we propose the greedy-based value representation (GVR), which turns the optimal node into an STN via inferior target shaping and eliminates the non-optimal STNs via superior experience replay. Theoretical proofs and empirical results demonstrate that given the true Q values, GVR ensures the optimal consistency under sufficient exploration. Besides, in tasks where the true Q values are unavailable, GVR achieves an adaptive trade-off between optimality and stability. Our method outperforms state-of-the-art baselines in experiments on various benchmarks.

Training of graph neural networks (GNNs) for large-scale node classification is challenging. A key difficulty lies in obtaining accurate hidden node representations while avoiding the neighborhood explosion problem. Here, we propose a new technique, named feature momentum (FM), that uses a momentum step to incorporate historical embeddings when updating feature representations. We develop two specific algorithms, known as GraphFM-IB and GraphFM-OB, that consider in-batch and out-of-batch data, respectively. GraphFM-IB applies FM to in-batch sampled data, while GraphFM-OB applies FM to out-of-batch data that are 1-hop neighborhood of in-batch data. We provide a convergence analysis for GraphFM-IB and some theoretical insight for GraphFM-OB. Empirically, we observe that GraphFM-IB can effectively alleviate the neighborhood explosion problem of existing methods. In addition, GraphFM-OB achieves promising performance on multiple large-scale graph datasets.

We propose Graph-Coupled Oscillator Networks (GraphCON), a novel framework for deep learning on graphs. It is based on discretizations of a second-order system of ordinary differential equations (ODEs), which model a network of nonlinear controlled and damped oscillators, coupled via the adjacency structure of the underlying graph. The flexibility of our framework permits any basic GNN layer (e.g. convolutional or attentional) as the coupling function, from which a multi-layer deep neural network is built up via the dynamics of the proposed ODEs. We relate the oversmoothing problem, commonly encountered in GNNs, to the stability of steady states of the underlying ODE and show that zero-Dirichlet energy steady states are not stable for our proposed ODEs. This demonstrates that the proposed framework mitigates the oversmoothing problem. Moreover, we prove that GraphCON mitigates the exploding and vanishing gradients problem to facilitate training of deep multi-layer GNNs. Finally, we show that our approach offers competitive performance with respect to the state-of-the-art on a variety of graph-based learning tasks.

Graph neural architecture search has shown great potentials for automatically designing graph neural network (GNN) architectures for graph classification tasks. However, when there is a distribution shift between training and testing graphs, the existing approaches fail to deal with the problem of adapting to unknown test graph structures since they only search for a fixed architecture for all graphs. To solve this problem, we propose a novel GRACES model which is able to generalize under distribution shifts through tailoring a customized GNN architecture suitable for each graph instance with unknown distribution. Specifically, we design a self-supervised disentangled graph encoder to characterize invariant factors hidden in diverse graph structures. Then, we propose a prototype-based architecture customization strategy to generate the most suitable GNN architecture weights in a continuous space for each graph instance. We further propose a customized super-network to share weights among different architectures for the sake of efficient training. Extensive experiments on both synthetic and real-world datasets demonstrate that our proposed GRACES model can adapt to diverse graph structures and achieve state-of-the-art performance for graph classification tasks under distribution shifts.

Zeroth-order (ZO) method has been shown to be a powerful method for solving the optimization problem where explicit expression of the gradients is difficult or infeasible to obtain. Recently, due to the practical value of the constrained problems, a lot of ZO Frank-Wolfe or projected ZO methods have been proposed. However, in many applications, we may have a very large number of nonconvex white/black-box constraints, which makes the existing zeroth-order methods extremely inefficient (or even not working) since they need to inquire function value of all the constraints and project the solution to the complicated feasible set. In this paper, to solve the nonconvex problem with a large number of white/black-box constraints, we proposed a doubly stochastic zeroth-order gradient method (DSZOG) with momentum method and adaptive step size. Theoretically, we prove DSZOG can converge to the $\epsilon$-stationary point of the constrained problem. Experimental results in two applications demonstrate the superiority of our method in terms of training time and accuracy compared with other ZO methods for the constrained problem.