NeurIPS 2021 论文列表

One principal approach for illuminating a black-box neural network is feature attribution, i.e. identifying the importance of input features for the network’s prediction. The predictive information of features is recently proposed as a proxy for the measure of their importance. So far, the predictive information is only identified for latent features by placing an information bottleneck within the network. We propose a method to identify features with predictive information in the input domain. The method results in fine-grained identification of input features' information and is agnostic to network architecture. The core idea of our method is leveraging a bottleneck on the input that only lets input features associated with predictive latent features pass through. We compare our method with several feature attribution methods using mainstream feature attribution evaluation experiments. The code is publicly available.

Generative modeling of multivariate time series has remained challenging partly due to the complex, non-deterministic dynamics across long-distance timesteps. In this paper, we propose deep probabilistic methods that combine state-space models (SSMs) with transformer architectures. In contrast to previously proposed SSMs, our approaches use attention mechanism to model non-Markovian dynamics in the latent space and avoid recurrent neural networks entirely. We also extend our models to include several layers of stochastic variables organized in a hierarchy for further expressiveness. Compared to transformer models, ours are probabilistic, non-autoregressive, and capable of generating diverse long-term forecasts with uncertainty estimates. Extensive experiments show that our models consistently outperform competitive baselines on various tasks and datasets, including time series forecasting and human motion prediction.

In this paper, we provide a theory of using graph neural networks (GNNs) for multi-node representation learning (where we are interested in learning a representation for a set of more than one node, such as link). We know that GNN is designed to learn single-node representations. When we want to learn a node set representation involving multiple nodes, a common practice in previous works is to directly aggregate the single-node representations obtained by a GNN into a joint node set representation. In this paper, we show a fundamental constraint of such an approach, namely the inability to capture the dependence between nodes in the node set, and argue that directly aggregating individual node representations does not lead to an effective joint representation for multiple nodes. Then, we notice that a few previous successful works for multi-node representation learning, including SEAL, Distance Encoding, and ID-GNN, all used node labeling. These methods first label nodes in the graph according to their relationships with the target node set before applying a GNN. Then, the node representations obtained in the labeled graph are aggregated into a node set representation. By investigating their inner mechanisms, we unify these node labeling techniques into a single and most general form---labeling trick. We prove that with labeling trick a sufficiently expressive GNN learns the most expressive node set representations, thus in principle solves any joint learning tasks over node sets. Experiments on one important two-node representation learning task, link prediction, verified our theory. Our work explains the superior performance of previous node-labeling-based methods, and establishes a theoretical foundation of using GNNs for multi-node representation learning.

We develop algorithms for private stochastic convex optimization that adapt to the hardness of the specific function we wish to optimize. While previous work provide worst-case bounds for arbitrary convex functions, it is often the case that the function at hand belongs to a smaller class that enjoys faster rates. Concretely, we show that for functions exhibiting $\kappa$-growth around the optimum, i.e., $f(x) \ge f(x^\star) + \lambda \kappa^{-1} \|x-x^\star\|_2^\kappa$ for $\kappa > 1$, our algorithms improve upon the standard ${\sqrt{d}}/{n\varepsilon}$ privacy rate to the faster $({\sqrt{d}}/{n\varepsilon})^{\tfrac{\kappa}{\kappa - 1}}$. Crucially, they achieve these rates without knowledge of the growth constant $\kappa$ of the function. Our algorithms build upon the inverse sensitivity mechanism, which adapts to instance difficulty [2], and recent localization techniques in private optimization [25]. We complement our algorithms with matching lower bounds for these function classes and demonstrate that our adaptive algorithm is simultaneously (minimax) optimal over all $\kappa \ge 1+c$ whenever $c = \Theta(1)$.

Recent experiments have shown that deep networks can approximate solutions to high-dimensional PDEs, seemingly escaping the curse of dimensionality. However, questions regarding the theoretical basis for such approximations, including the required network size remain open. In this paper, we investigate the representational power of neural networks for approximating solutions to linear elliptic PDEs with Dirichlet boundary conditions. We prove that when a PDE's coefficients are representable by small neural networks, the parameters required to approximate its solution scale polynomially with the input dimension $d$ and proportionally to the parameter counts of the coefficient networks. To this end, we develop a proof technique that simulates gradient descent (in an appropriate Hilbert space) by growing a neural network architecture whose iterates each participate as sub-networks in their (slightly larger) successors, and converge to the solution of the PDE.

We present a new second-order oracle bound for the expected risk of a weighted majority vote. The bound is based on a novel parametric form of the Chebyshev-Cantelli inequality (a.k.a. one-sided Chebyshev’s), which is amenable to efficient minimization. The new form resolves the optimization challenge faced by prior oracle bounds based on the Chebyshev-Cantelli inequality, the C-bounds [Germain et al., 2015], and, at the same time, it improves on the oracle bound based on second order Markov’s inequality introduced by Masegosa et al. [2020]. We also derive a new concentration of measure inequality, which we name PAC-Bayes-Bennett, since it combines PAC-Bayesian bounding with Bennett’s inequality. We use it for empirical estimation of the oracle bound. The PAC-Bayes-Bennett inequality improves on the PAC-Bayes-Bernstein inequality of Seldin et al. [2012]. We provide an empirical evaluation demonstrating that the new bounds can improve on the work of Masegosa et al. [2020]. Both the parametric form of the Chebyshev-Cantelli inequality and the PAC-Bayes-Bennett inequality may be of independent interest for the study of concentration of measure in other domains.

Meta-Learning promises to enable more data-efficient inference by harnessing previous experience from related learning tasks. While existing meta-learning methods help us to improve the accuracy of our predictions in face of data scarcity, they fail to supply reliable uncertainty estimates, often being grossly overconfident in their predictions. Addressing these shortcomings, we introduce a novel meta-learning framework, called F-PACOH, that treats meta-learned priors as stochastic processes and performs meta-level regularization directly in the function space. This allows us to directly steer the probabilistic predictions of the meta-learner towards high epistemic uncertainty in regions of insufficient meta-training data and, thus, obtain well-calibrated uncertainty estimates. Finally, we showcase how our approach can be integrated with sequential decision making, where reliable uncertainty quantification is imperative. In our benchmark study on meta-learning for Bayesian Optimization (BO), F-PACOH significantly outperforms all other meta-learners and standard baselines. Even in a challenging lifelong BO setting, where optimization tasks arrive one at a time and the meta-learner needs to build up informative prior knowledge incrementally, our proposed method demonstrates strong positive transfer.

Energy-based models (EBMs) provide an elegant framework for density estimation, but they are notoriously difficult to train. Recent work has established links to generative adversarial networks, where the EBM is trained through a minimax game with a variational value function. We propose a bidirectional bound on the EBM log-likelihood, such that we maximize a lower bound and minimize an upper bound when solving the minimax game. We link one bound to a gradient penalty that stabilizes training, thereby provide grounding for best engineering practice. To evaluate the bounds we develop a new and efficient estimator of the Jacobi-determinant of the EBM generator. We demonstrate that these developments stabilize training and yield high-quality density estimation and sample generation.

We investigate how to exploit structural similarities of an individual's potential outcomes (POs) under different treatments to obtain better estimates of conditional average treatment effects in finite samples. Especially when it is unknown whether a treatment has an effect at all, it is natural to hypothesize that the POs are similar -- yet, some existing strategies for treatment effect estimation employ regularization schemes that implicitly encourage heterogeneity even when it does not exist and fail to fully make use of shared structure. In this paper, we investigate and compare three end-to-end learning strategies to overcome this problem -- based on regularization, reparametrization and a flexible multi-task architecture -- each encoding inductive bias favoring shared behavior across POs. To build understanding of their relative strengths, we implement all strategies using neural networks and conduct a wide range of semi-synthetic experiments. We observe that all three approaches can lead to substantial improvements upon numerous baselines and gain insight into performance differences across various experimental settings.

We consider Bayesian optimization of the output of a network of functions, where each function takes as input the output of its parent nodes, and where the network takes significant time to evaluate. Such problems arise, for example, in reinforcement learning, engineering design, and manufacturing. While the standard Bayesian optimization approach observes only the final output, our approach delivers greater query efficiency by leveraging information that the former ignores: intermediate output within the network. This is achieved by modeling the nodes of the network using Gaussian processes and choosing the points to evaluate using, as our acquisition function, the expected improvement computed with respect to the implied posterior on the objective. Although the non-Gaussian nature of this posterior prevents computing our acquisition function in closed form, we show that it can be efficiently maximized via sample average approximation. In addition, we prove that our method is asymptotically consistent, meaning that it finds a globally optimal solution as the number of evaluations grows to infinity, thus generalizing previously known convergence results for the expected improvement. Notably, this holds even though our method might not evaluate the domain densely, instead leveraging problem structure to leave regions unexplored. Finally, we show that our approach dramatically outperforms standard Bayesian optimization methods in several synthetic and real-world problems.

Tracking objects of interest in a video is one of the most popular and widely applicable problems in computer vision. However, with the years, a Cambrian explosion of use cases and benchmarks has fragmented the problem in a multitude of different experimental setups. As a consequence, the literature has fragmented too, and now novel approaches proposed by the community are usually specialised to fit only one specific setup. To understand to what extent this specialisation is necessary, in this work we present UniTrack, a solution to address five different tasks within the same framework. UniTrack consists of a single and task-agnostic appearance model, which can be learned in a supervised or self-supervised fashion, and multiple ``heads'' that address individual tasks and do not require training. We show how most tracking tasks can be solved within this framework, and that the same appearance model can be successfully used to obtain results that are competitive against specialised methods for most of the tasks considered. The framework also allows us to analyse appearance models obtained with the most recent self-supervised methods, thus extending their evaluation and comparison to a larger variety of important problems.

Effectively predicting molecular interactions has the potential to accelerate molecular dynamics by multiple orders of magnitude and thus revolutionize chemical simulations. Graph neural networks (GNNs) have recently shown great successes for this task, overtaking classical methods based on fixed molecular kernels. However, they still appear very limited from a theoretical perspective, since regular GNNs cannot distinguish certain types of graphs. In this work we close this gap between theory and practice. We show that GNNs with directed edge embeddings and two-hop message passing are indeed universal approximators for predictions that are invariant to translation, and equivariant to permutation and rotation. We then leverage these insights and multiple structural improvements to propose the geometric message passing neural network (GemNet). We demonstrate the benefits of the proposed changes in multiple ablation studies. GemNet outperforms previous models on the COLL, MD17, and OC20 datasets by 34%, 41%, and 20%, respectively, and performs especially well on the most challenging molecules. Our implementation is available online.

In this dataset paper we introduce PROCAT, a novel e-commerce dataset containing expertly designed product catalogues consisting of individual product offers grouped into complementary sections. We aim to address the scarcity of existing datasets in the area of set-to-sequence machine learning tasks, which involve complex structure prediction. The task's difficulty is further compounded by the need to place into sequences rare and previously-unseen instances, as well as by variable sequence lengths and substructures, in the form of diversely-structured catalogues. PROCAT provides catalogue data consisting of over 1.5 million set items across a 4-year period, in both raw text form and with pre-processed features containing information about relative visual placement. In addition to this ready-to-use dataset, we include baseline experimental results on a proposed benchmark task from a number of joint set encoding and permutation learning model architectures.

Traditional seismic inversion (SI) maps the hundreds of terabytes of raw-field data to subsurface properties in gigabytes. This inversion process is expensive, requiring over a year of human and computational effort. Recently, data-driven approaches equipped with Deep learning (DL) are envisioned to improve SI efficiency. However, these improvements are restricted to data with highly reduced scale and complexity. To extend these approaches to real-scale seismic data, researchers need to process raw nav-merge seismic data into an image and perform convolution. We argue that this convolution-based way of SI is not only computationally expensive but also conceptually problematic. Seismic data is not naturally an image and need not be processed as images. In this work, we go beyond convolution and propose a novel SI method. We solve the scalability of SI by proposing a new auxiliary learning paradigm for SI (Aux-SI). This paradigm breaks the SI into local inversion tasks, which predicts each small chunk of subsurface properties using surrounding seismic data. Aux-SI combines these local predictions to obtain the entire subsurface model. However, even this local inversion is still challenging due to: (1) high-dimensional, spatially irregular multi-modal seismic data, (2) there is no concrete spatial mapping (or alignment) between subsurface properties and raw data. To handle these challenges, we propose an all-MLP architecture, Multi-Modal Information Unscrambler (MMI-Unscrambler), that unscrambles seismic information by ingesting all available multi-modal data. The experiment shows that MMI-Unscrambler outperforms both SOTA U-Net and Transformer models on simulation data. We also scale MMI-Unscrambler to raw-field nav-merge data on Gulf-of-Mexico to obtain a geologically sound velocity model with an SSIM score of 0.8. To the best of our knowledge, this is the first successful demonstration of the DL approach on SI for real, large-scale, and complicated raw field data.

Channel pruning is a popular technique for compressing convolutional neural networks (CNNs), where various pruning criteria have been proposed to remove the redundant filters. From our comprehensive experiments, we found two blind spots of pruning criteria: (1) Similarity: There are some strong similarities among several primary pruning criteria that are widely cited and compared. According to these criteria, the ranks of filters’ Importance Score are almost identical, resulting in similar pruned structures. (2) Applicability: The filters' Importance Score measured by some pruning criteria are too close to distinguish the network redundancy well. In this paper, we analyze the above blind spots on different types of pruning criteria with layer-wise pruning or global pruning. We also break some stereotypes, such as that the results of $\ell_1$ and $\ell_2$ pruning are not always similar. These analyses are based on the empirical experiments and our assumption (Convolutional Weight Distribution Assumption) that the well-trained convolutional filters in each layer approximately follow a Gaussian-alike distribution. This assumption has been verified through systematic and extensive statistical tests.

Learning efficiently from small amounts of data has long been the focus of model-based reinforcement learning, both for the online case when interacting with the environment, and the offline case when learning from a fixed dataset. However, to date no single unified algorithm could demonstrate state-of-the-art results for both settings. In this work, we describe the Reanalyse algorithm, which uses model-based policy and value improvement operators to compute improved training targets for existing data points, allowing for efficient learning at data budgets varying by several orders of magnitude. We further show that Reanalyse can also be used to learn completely without environment interactions, as in the case of Offline Reinforcement Learning (Offline RL). Combining Reanalyse with the MuZero algorithm, we introduce MuZero Unplugged, a single unified algorithm for any data budget, including Offline RL. In contrast to previous work, our algorithm requires no special adaptations for the off-policy or Offline RL settings. MuZero Unplugged sets new state-of-the-art results for Atari in the standard 200 million frame online setting as well as in the RL Unplugged Offline RL benchmark.

We seek an entropy estimator for discrete distributions with fully empirical accuracy bounds. As stated, this goal is infeasible without some prior assumptions on the distribution. We discover that a certain information moment assumption renders the problem feasible. We argue that the moment assumption is natural and, in some sense, {\em minimalistic} --- weaker than finite support or tail decay conditions. Under the moment assumption, we provide the first finite-sample entropy estimates for infinite alphabets, nearly recovering the known minimax rates. Moreover, we demonstrate that our empirical bounds are significantly sharper than the state-of-the-art bounds, for various natural distributions and non-trivial sample regimes. Along the way, we give a dimension-free analogue of the Cover-Thomas result on entropy continuity (with respect to total variation distance) for finite alphabets, which may be of independent interest.

The Text-to-SQL task, aiming to translate the natural language of the questions into SQL queries, has drawn much attention recently. One of the most challenging problems of Text-to-SQL is how to generalize the trained model to the unseen database schemas, also known as the cross-domain Text-to-SQL task. The key lies in the generalizability of (i) the encoding method to model the question and the database schema and (ii) the question-schema linking method to learn the mapping between words in the question and tables/columns in the database schema. Focusing on the above two key issues, we propose a \emph{Structure-Aware Dual Graph Aggregation Network} (SADGA) for cross-domain Text-to-SQL. In SADGA, we adopt the graph structure to provide a unified encoding model for both the natural language question and database schema. Based on the proposed unified modeling, we further devise a structure-aware aggregation method to learn the mapping between the question-graph and schema-graph. The structure-aware aggregation method is featured with \emph{Global Graph Linking}, \emph{Local Graph Linking} and \emph{Dual-Graph Aggregation Mechanism}. We not only study the performance of our proposal empirically but also achieved 3rd place on the challenging Text-to-SQL benchmark Spider at the time of writing.

We study data clustering problems with $\ell_p$-norm objectives (e.g. \textsc{$k$-Median} and \textsc{$k$-Means}) in the context of individual fairness. The dataset consists of $n$ points, and we want to find $k$ centers such that (a) the objective is minimized, while (b) respecting the individual fairness constraint that every point $v$ has a center within a distance at most $r(v)$, where $r(v)$ is $v$'s distance to its $(n/k)$th nearest point. Jung, Kannan, and Lutz [FORC 2020] introduced this concept and designed a clustering algorithm with provable (approximate) fairness and objective guarantees for the $\ell_\infty$ or \textsc{$k$-Center} objective. Mahabadi and Vakilian [ICML 2020] revisited this problem to give a local-search algorithm for all $\ell_p$-norms. Empirically, their algorithms outperform Jung et. al.'s by a large margin in terms of cost (for \textsc{$k$-Median} and \textsc{$k$-Means}), but they incur a reasonable loss in fairness. In this paper, our main contribution is to use Linear Programming (LP) techniques to obtain better algorithms for this problem, both in theory and in practice. We prove that by modifying known LP rounding techniques, one gets a worst-case guarantee on the objective which is much better than in MV20, and empirically, this objective is extremely close to the optimal. Furthermore, our theoretical fairness guarantees are comparable with MV20 in theory, and empirically, we obtain noticeably fairer solutions. Although solving the LP {\em exactly} might be prohibitive, we demonstrate that in practice, a simple sparsification technique drastically improves the run-time of our algorithm.