ICLR 2023 Papers

Rich data and powerful machine learning models allow us to design drugs for a specific protein target <em>in silico</em>. Recently, the inclusion of 3D structures during targeted drug design shows superior performance to other target-free models as the atomic interaction in the 3D space is explicitly modeled. However, current 3D target-aware models either rely on the voxelized atom densities or the autoregressive sampling process, which are not equivariant to rotation or easily violate geometric constraints resulting in unrealistic structures. In this work, we develop a 3D equivariant diffusion model to solve the above challenges. To achieve target-aware molecule design, our method learns a joint generative process of both continuous atom coordinates and categorical atom types with a SE(3)-equivariant network. Moreover, we show that our model can serve as an unsupervised feature extractor to estimate the binding affinity under proper parameterization, which provides an effective way for drug screening. To evaluate our model, we propose a comprehensive framework to evaluate the quality of sampled molecules from different dimensions. Empirical studies show our model could generate molecules with more realistic 3D structures and better affinities towards the protein targets, and improve binding affinity ranking and prediction without retraining.

We propose the Gradient-weighted Object Detector Activation Mapping (Grad-ODAM), a visualized explanation technique for interpreting the predictions of object detectors. Utilizing the gradients of detector targets flowing into the intermediate feature maps, Grad-ODAM produces heat maps that show the influence of regions on the detector's decision. Compared to previous classification activation mapping works, Grad-ODAM generates instance-specific explanations rather than class-specific ones. We show that Grad-ODAM is applicable to both one-stage detectors such as FCOS and two-stage detectors such as Faster R-CNN, and produces higher-quality visual explanations than the state-of-the-art both effectively and efficiently. We next propose a training scheme, ODAM-Train, to improve the explanation ability on object discrimination of the detector through encouraging consistency between explanations for detections on the same object, and distinct explanations for detections on different objects. Based on the heat maps produced by Grad-ODAM with ODAM-Train, we propose ODAM-NMS, which considers the information of the model's explanation for each prediction to distinguish the duplicate detected objects. We present a detailed analysis of the visualized explanations of detectors and carry out extensive experiments to validate the effectiveness of the proposed ODAM.

Coupled partial differential equations (PDEs) are key tasks in modeling the complex dynamics of many physical processes. Recently, neural operators have shown the ability to solve PDEs by learning the integral kernel directly in Fourier/Wavelet space, so the difficulty of solving the coupled PDEs depends on dealing with the coupled mappings between the functions. Towards this end, we propose a \textit{coupled multiwavelets neural operator} (CMWNO) learning scheme by decoupling the coupled integral kernels during the multiwavelet decomposition and reconstruction procedures in the Wavelet space. The proposed model achieves significantly higher accuracy compared to previous learning-based solvers in solving the coupled PDEs including Gray-Scott (GS) equations and the non-local mean field game (MFG) problem. According to our experimental results, the proposed model exhibits a $2X-4X$ improvement relative $L$2 error compared to the best results from the state-of-the-art models.

Unsupervised meta-learning (UML) essentially shares the spirit of self-supervised learning (SSL) in that their goal aims at learning models without any human supervision so that the models can be adapted to downstream tasks. Further, the learning objective of self-supervised learning, which pulls positive pairs closer and repels negative pairs, also resembles metric-based meta-learning. Metric-based meta-learning is one of the most successful meta-learning methods, which learns to minimize the distance between representations from the same class. One notable aspect of metric-based meta-learning, however, is that it is widely interpreted as a set-level problem since the inference of discriminative class prototypes (or set representations) from few examples is crucial for the performance of downstream tasks. Motivated by this, we propose Set-SimCLR, a novel self-supervised set representation learning framework for targeting UML problem. Specifically, our Set-SimCLR learns a set encoder on top of instance representations to maximize the agreement between two sets of augmented samples, which are generated by applying stochastic augmentations to a given image. We theoretically analyze how our proposed set representation learning can potentially improve the generalization performance at the meta-test. We also empirically validate its effectiveness on various benchmark datasets, showing that Set-SimCLR largely outperforms both UML and instance-level self-supervised learning baselines.

Message Passing Neural Networks (MPNNs) are a widely used class of Graph Neural Networks (GNNs). The limited representational power of MPNNs inspires the study of provably powerful GNN architectures. However, knowing one model is more powerful than another gives little insight about what functions they can or cannot express. It is still unclear whether these models are able to approximate specific functions such as counting certain graph substructures, which is essential for applications in biology, chemistry and social network analysis. Motivated by this, we propose to study the counting power of Subgraph MPNNs, a recent and popular class of powerful GNN models that extract rooted subgraphs for each node, assign the root node a unique identifier and encode the root node's representation within its rooted subgraph. Specifically, we prove that Subgraph MPNNs fail to count more-than-4-cycles at node level, implying that node representations cannot correctly encode the surrounding substructures like ring systems with more than four atoms. To overcome this limitation, we propose I$^2$-GNNs to extend Subgraph MPNNs by assigning different identifiers for the root node and its neighbors in each subgraph. I$^2$-GNNs' discriminative power is shown to be strictly stronger than Subgraph MPNNs and partially stronger than the 3-WL test. More importantly, I$^2$-GNNs are proven capable of counting all 3, 4, 5 and 6-cycles, covering common substructures like benzene rings in organic chemistry, while still keeping linear complexity. To the best of our knowledge, it is the first linear-time GNN model that can count 6-cycles with theoretical guarantees. We validate its counting power in cycle counting tasks and demonstrate its competitive performance in molecular prediction benchmarks.

Overparameterization in deep learning refers to settings where a trained Neural Network (NN) has representational capacity to fit the training data in many ways, some of which generalize well, while others do not. In the case of Recurrent Neural Networks (RNNs) there exists an additional layer of overparameterization, in the sense that a model may exhibit many solutions that generalize well for sequence lengths seen in training, some of which \emph{extrapolate} to longer sequences, while others do not. Numerous works studied the tendency of Gradient Descent (GD) to fit overparameterized NNs with solutions that generalize well. On the other hand, its tendency to fit overparameterized RNNs with solutions that extrapolate has been discovered only lately, and is far less understood. In this paper, we analyze the extrapolation properties of GD when applied to overparameterized linear RNNs. In contrast to recent arguments suggesting an implicit bias towards short-term memory, we provide theoretical evidence for learning low dimensional state spaces, which can also model long-term memory. Our result relies on a dynamical characterization showing that GD (with small step size and near zero initialization) strives to maintain a certain form of balancedness, as well as tools developed in the context of the \emph{moment problem} from statistics (recovery of discrete probability distribution from its moments). Experiments corroborate our theory, demonstrating extrapolation via learning low dimensional state spaces with both linear and non-linear RNNs.

With adversarial or otherwise normal prompts, existing large language models (LLM) can be pushed to generate toxic discourses. One way to reduce the risk of LLMs generating undesired discourses is to alter the training of the LLM. This can be very restrictive due to demanding computation requirements. Other methods rely on rule-based or prompt-based token elimination, which are limited as they dismiss future tokens and the overall meaning of the complete discourse. Here, we center detoxification on the probability that the finished discourse is ultimately considered toxic. That is, at each point, we advise against token selections proportional to how likely a finished text from this point will be toxic. To this end, we formally extend the dead-end theory from the recent reinforcement learning (RL) literature to also cover uncertain outcomes. Our approach, called rectification, utilizes a separate but significantly smaller model for detoxification, which can be applied to diverse LLMs as long as they share the same vocabulary. Importantly, our method does not require access to the internal representations of the LLM, but only the token probability distribution at each decoding step. We believe this is important since many LLMs today are hosted in servers and only accessible through APIs. When applied to various LLMs, including GPT-3, our approach generates notably better results compared to the base LLMs and other techniques in terms of the overall language and detoxification performance.

Open-domain dialogue systems aim to interact with humans through natural language texts in an open-ended fashion. Despite the recent success of super large dialogue systems such as ChatGPT, using medium-to-small-sized dialogue systems remains the common practice as they are more lightweight and accessible; however, generating diverse dialogue responses is challenging, especially with smaller models. In this work, we propose an Equal-size Hard Expectation--Maximization (EqHard-EM) algorithm to train a multi-decoder model for diverse dialogue generation. Our algorithm assigns a sample to a decoder in a hard manner and additionally imposes an equal-assignment constraint to ensure that all decoders are well-trained. We provide detailed theoretical analysis to justify our approach. Further, experiments on two large-scale open-domain dialogue datasets verify that our EqHard-EM algorithm generates high-quality diverse responses.

One main challenge in federated learning is the large communication cost of exchanging weight updates from clients to the server at each round. While prior work has made great progress in compressing the weight updates through gradient compression methods, we propose a radically different approach that does not update the weights at all. Instead, our method freezes the weights at their initial \emph{random} values and learns how to sparsify the random network for the best performance. To this end, the clients collaborate in training a \emph{stochastic} binary mask to find the optimal sparse random network within the original one. At the end of the training, the final model is a sparse network with random weights -- or a subnetwork inside the dense random network. We show improvements in accuracy, communication (less than $1$ bit per parameter (bpp)), convergence speed, and final model size (less than $1$ bpp) over relevant baselines on MNIST, EMNIST, CIFAR-10, and CIFAR-100 datasets, in the low bitrate regime.

Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM) demonstrate that self-supervision is powerful to learn good representations. However, naively combining them is far from success. In this paper, we start by making the empirical observation that a naive joint optimization of CL and MIM losses leads to conflicting gradient directions - more severe as the layers go deeper. This motivates us to shift the paradigm from combining loss at the end, to choosing the proper learning method per network layer. Inspired by experimental observations, we find that MIM and CL are suitable to lower and higher layers, respectively. We hence propose to combine them in a surprisingly simple, ``sequential cascade'' fashion: early layers are first trained under one MIM loss, on top of which latter layers continue to be trained under another CL loss. The proposed Layer Grafted Pre-training learns good visual representations that demonstrate superior label efficiency in downstream applications, in particular yielding strong few-shot performance besides linear evaluation. For instance, on ImageNet-1k, Layer Grafted Pre-training yields 65.5% Top-1 accuracy in terms of 1% few-shot learning with ViT-B/16, which improves MIM and CL baselines by 14.4% and 2.1% with no bells and whistles. The code is available at https://github.com/VITA-Group/layerGraftedPretraining_ICLR23.git.

Time series analysis is of immense importance in extensive applications, such as weather forecasting, anomaly detection, and action recognition. This paper focuses on temporal variation modeling, which is the common key problem of extensive analysis tasks. Previous methods attempt to accomplish this directly from the 1D time series, which is extremely challenging due to the intricate temporal patterns. Based on the observation of multi-periodicity in time series, we ravel out the complex temporal variations into the multiple intraperiod- and interperiod-variations. To tackle the limitations of 1D time series in representation capability, we extend the analysis of temporal variations into the 2D space by transforming the 1D time series into a set of 2D tensors based on multiple periods. This transformation can embed the intraperiod- and interperiod-variations into the columns and rows of the 2D tensors respectively, making the 2D-variations to be easily modeled by 2D kernels. Technically, we propose the TimesNet with TimesBlock as a task-general backbone for time series analysis. TimesBlock can discover the multi-periodicity adaptively and extract the complex temporal variations from transformed 2D tensors by a parameter-efficient inception block. Our proposed TimesNet achieves consistent state-of-the-art in five mainstream time series analysis tasks, including short- and long-term forecasting, imputation, classification, and anomaly detection. Code is available at this repository: https://github.com/thuml/TimesNet.

Physical simulations that accurately model reality are crucial for many engineering disciplines such as mechanical engineering and robotic motion planning. In recent years, learned Graph Network Simulators produced accurate mesh-based simulations while requiring only a fraction of the computational cost of traditional simulators. Yet, the resulting predictors are confined to learning from data generated by existing mesh-based simulators and thus cannot include real world sensory information such as point cloud data. As these predictors have to simulate complex physical systems from only an initial state, they exhibit a high error accumulation for long-term predictions. In this work, we integrate sensory information to ground Graph Network Simulators on real world observations. In particular, we predict the mesh state of deformable objects by utilizing point cloud data. The resulting model allows for accurate predictions over longer time horizons, even under uncertainties in the simulation, such as unknown material properties. Since point clouds are usually not available for every time step, especially in online settings, we employ an imputation-based model. The model can make use of such additional information only when provided, and resorts to a standard Graph Network Simulator, otherwise. We experimentally validate our approach on a suite of prediction tasks for mesh-based interactions between soft and rigid bodies. Our method results in utilization of additional point cloud information to accurately predict stable simulations where existing Graph Network Simulators fail.

In reward-free reinforcement learning (RL), an agent explores the environment first without any reward information, in order to achieve certain learning goals afterwards for any given reward. In this paper we focus on reward-free RL under low-rank MDP models, in which both the representation and linear weight vectors are unknown. Although various algorithms have been proposed for reward-free low-rank MDPs, the corresponding sample complexity is still far from being satisfactory. In this work, we first provide the first known sample complexity lower bound that holds for any algorithm under low-rank MDPs. This lower bound implies it is strictly harder to find a near-optimal policy under low-rank MDPs than under linear MDPs. We then propose a novel model-based algorithm, coined RAFFLE, and show it can both find an $\epsilon$-optimal policy and achieve an $\epsilon$-accurate system identification via reward-free exploration, with a sample complexity significantly improving the previous results. Such a sample complexity matches our lower bound in the dependence on $\epsilon$, as well as on $K$ {in the large $d$ regime}, where $d$ and $K$ respectively denote the representation dimension and action space cardinality. Finally, we provide a planning algorithm (without further interaction with true environment) for RAFFLE to learn a near-accurate representation, which is the first known representation learning guarantee under the same setting.

Partial label learning (PLL) tackles the problem where each instance is associated with a set of candidate labels, only one of which is the ground-truth label. Most existing PLL approaches assume that both the training and test sets share an identical data distribution. However, this assumption does not hold in many real-world scenarios where the training and test data come from different distributions. In this paper, we formalize this learning scenario as a new problem called partial label unsupervised domain adaptation (PLUDA). To address this challenging PLUDA problem, we propose a novel Prototype Alignment based PLUDA method named PAPLUDA, which dynamically refines the pseudo-labels of instances from both the source and target domains by consulting the outputs of a teacher-student model in a moving-average manner, and bridges the cross-domain discrepancy through inter-domain class-prototype alignment. In addition, a teacher-student model based contrastive regularization is deployed to enhance prediction stability and hence improve the class-prototypes in both domains for PLUDA. Comprehensive experimental results demonstrate that PAPLUDA achieves state-of-the-art performance on the widely used benchmark datasets.

Edge devices provide inference on predictive tasks to many end-users. However, deploying deep neural networks that achieve state-of-the-art accuracy on these devices is infeasible due to edge resource constraints. Nevertheless, cloud-only processing, the de-facto standard, is also problematic, since uploading large amounts of data imposes severe communication bottlenecks. We propose a novel end-to-end hybrid learning framework that allows the edge to selectively query only those hard examples that the cloud can classify correctly. Our framework optimizes over neural architectures and trains edge predictors and routing models so that the overall accuracy remains high while minimizing the overall latency. Training a hybrid learner is difficult since we lack annotations of hard edge-examples. We introduce a novel proxy supervision in this context and show that our method adapts seamlessly and near optimally across different latency regimes. On the ImageNet dataset, our proposed method deployed on a micro-controller unit exhibits $25\%$ reduction in latency compared to cloud-only processing while suffering no excess loss.

The decentralized Federated Learning (FL) setting avoids the role of a potentially unreliable or untrustworthy central host by utilizing groups of clients to collaboratively train a model via localized training and model/gradient sharing. Most existing decentralized FL algorithms require synchronization of client models where the speed of synchronization depends upon the slowest client. In this work, we propose SWIFT: a novel wait-free decentralized FL algorithm that allows clients to conduct training at their own speed. Theoretically, we prove that SWIFT matches the gold-standard iteration convergence rate $\mathcal{O}(1/\sqrt{T})$ of parallel stochastic gradient descent for convex and non-convex smooth optimization (total iterations $T$). Furthermore, we provide theoretical results for IID and non-IID settings without any bounded-delay assumption for slow clients which is required by other asynchronous decentralized FL algorithms. Although SWIFT achieves the same iteration convergence rate with respect to $T$ as other state-of-the-art (SOTA) parallel stochastic algorithms, it converges faster with respect to runtime due to its wait-free structure. Our experimental results demonstrate that SWIFT's runtime is reduced due to a large reduction in communication time per epoch, which falls by an order of magnitude compared to synchronous counterparts. Furthermore, SWIFT produces loss levels for image classification, over IID and non-IID data settings, upwards of 50\% faster than existing SOTA algorithms.

Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over the years. Existing literature mainly focus on selecting a subgraph, through combinatorial optimization, to provide faithful explanations. However, the exponential size of candidate subgraphs limits the applicability of state-of-the-art methods to large-scale GNNs. We enhance on this through a different approach: by proposing a generative structure – GFlowNets-based GNN Explainer (GFlowExplainer), we turn the optimization problem into a step-by-step generative problem. Our GFlowExplainer aims to learn a policy that generates a distribution of subgraphs for which the probability of a subgraph is proportional to its’ reward. The proposed approach eliminates the influence of node sequence and thus does not need any pre-training strategies. We also propose a new cut vertex matrix to efficiently explore parent states for GFlowNets structure, thus making our approach applicable in a large-scale setting. We conduct extensive experiments on both synthetic and real datasets, and both qualitative and quantitative results show the superiority of our GFlowExplainer.

Recent years have witnessed the prosperity of pre-training graph neural networks (GNNs) for molecules. Typically, atom types as node attributes are randomly masked, and GNNs are then trained to predict masked types as in AttrMask \citep{hu2020strategies}, following the Masked Language Modeling (MLM) task of BERT~\citep{devlin2019bert}. However, unlike MLM with a large vocabulary, the AttrMask pre-training does not learn informative molecular representations due to small and unbalanced atom `vocabulary'. To amend this problem, we propose a variant of VQ-VAE~\citep{van2017neural} as a context-aware tokenizer to encode atom attributes into chemically meaningful discrete codes. This can enlarge the atom vocabulary size and mitigate the quantitative divergence between dominant (e.g., carbons) and rare atoms (e.g., phosphorus). With the enlarged atom `vocabulary', we propose a novel node-level pre-training task, dubbed Masked Atoms Modeling (\textbf{MAM}), to mask some discrete codes randomly and then pre-train GNNs to predict them. MAM also mitigates another issue of AttrMask, namely the negative transfer. It can be easily combined with various pre-training tasks to improve their performance. Furthermore, we propose triplet masked contrastive learning (\textbf{TMCL}) for graph-level pre-training to model the heterogeneous semantic similarity between molecules for effective molecule retrieval. MAM and TMCL constitute a novel pre-training framework, \textbf{Mole-BERT}, which can match or outperform state-of-the-art methods in a fully data-driven manner. We release the code at \textcolor{magenta}{\url{https://github.com/junxia97/Mole-BERT}}.

Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints. While prior works focus on the performance optimality, we find that the optimal solutions of many safe RL problems are not robust and safe against carefully designed observational perturbations. We formally analyze the unique properties of designing effective observational adversarial attackers in the safe RL setting. We show that baseline adversarial attack techniques for standard RL tasks are not always effective for safe RL and propose two new approaches - one maximizes the cost and the other maximizes the reward. One interesting and counter-intuitive finding is that the maximum reward attack is strong, as it can both induce unsafe behaviors and make the attack stealthy by maintaining the reward. We further propose a robust training framework for safe RL and evaluate it via comprehensive experiments. This paper provides a pioneer work to investigate the safety and robustness of RL under observational attacks for future safe RL studies. Code is available at: \url{https://github.com/liuzuxin/safe-rl-robustness}