ICLR 2023 论文列表

The Teacher-Student Framework (TSF) is a reinforcement learning setting where a teacher agent guards the training of a student agent by intervening and providing online demonstrations. Assuming optimal, the teacher policy has the perfect timing and capability to intervene in the learning process of the student agent, providing safety guarantee and exploration guidance. Nevertheless, in many real-world settings it is expensive or even impossible to obtain a well-performing teacher policy. In this work, we relax the assumption of a well-performing teacher and develop a new method that can incorporate arbitrary teacher policies with modest or inferior performance. We instantiate an Off-Policy Reinforcement Learning algorithm, termed Teacher-Student Shared Control (TS2C), which incorporates teacher intervention based on trajectory-based value estimation. Theoretical analysis validates that the proposed TS2C algorithm attains efficient exploration and substantial safety guarantee without being affected by the teacher's own performance. Experiments on various continuous control tasks show that our method can exploit teacher policies at different performance levels while maintaining a low training cost. Moreover, the student policy surpasses the imperfect teacher policy in terms of higher accumulated reward in held-out testing environments. Code is available at https://metadriverse.github.io/TS2C.

Human similarity judgments are a powerful supervision signal for machine learning applications based on techniques such as contrastive learning, information retrieval, and model alignment, but classical methods for collecting human similarity judgments are too expensive to be used at scale. Recent methods propose using pre-trained deep neural networks (DNNs) to approximate human similarity, but pre-trained DNNs may not be available for certain domains (e.g., medical images, low-resource languages) and their performance in approximating human similarity has not been extensively tested. We conducted an evaluation of 611 pre-trained models across three domains -- images, audio, video -- and found that there is a large gap in performance between human similarity judgments and pre-trained DNNs. To address this gap, we propose a new class of similarity approximation methods based on language. To collect the language data required by these new methods, we also developed and validated a novel adaptive tag collection pipeline. We find that our proposed language-based methods are significantly cheaper, in the number of human judgments, than classical methods, but still improve performance over the DNN-based methods. Finally, we also develop `stacked' methods that combine language embeddings with DNN embeddings, and find that these consistently provide the best approximations for human similarity across all three of our modalities. Based on the results of this comprehensive study, we provide a concise guide for researchers interested in collecting or approximating human similarity data. To accompany this guide, we also release all of the similarity and language data, a total of 206,339 human judgments, that we collected in our experiments, along with a detailed breakdown of all modeling results.

Recent symbolic music generative models have achieved significant improvements in the quality of the generated samples. Nevertheless, it remains hard for users to control the output in such a way that it matches their expectation. To address this limitation, high-level, human-interpretable conditioning is essential. In this work, we release FIGARO, a Transformer-based conditional model trained to generate symbolic music based on a sequence of high-level control codes. To this end, we propose description-to-sequence learning, which consists of automatically extracting fine-grained, human-interpretable features (the description) and training a sequence-to-sequence model to reconstruct the original sequence given only the description as input. FIGARO achieves state-of-the-art performance in multi-track symbolic music generation both in terms of style transfer and sample quality. We show that performance can be further improved by combining human-interpretable with learned features. Our extensive experimental evaluation shows that FIGARO is able to generate samples that closely adhere to the content of the input descriptions, even when they deviate significantly from the training distribution.

Research in mechanistic interpretability seeks to explain behaviors of ML models in terms of their internal components. However, most previous work either focuses on simple behaviors in small models, or describes complicated behaviors in larger models with broad strokes. In this work, we bridge this gap by presenting an explanation for how GPT-2 small performs a natural language task that requires logical reasoning: indirect object identification (IOI). Our explanation encompasses 28 attention heads grouped into 7 main classes, which we discovered using a combination of interpretability approaches including causal interventions and projections. To our knowledge, this investigation is the largest end-to-end attempt at reverse-engineering a natural behavior "in the wild" in a language model. We evaluate the reliability of our explanation using three quantitative criteria - faithfulness, completeness and minimality. Though these criteria support our explanation, they also point to remaining gaps in our understanding. Our work provides evidence that a mechanistic understanding of large ML models is feasible, opening opportunities to scale our understanding to both larger models and more complex tasks.

The emergence of various multi-agent environments has motivated powerful algorithms to explore agents' cooperation or competition. Even though this has greatly promoted the development of multi-agent reinforcement learning (MARL), it is still not enough to support further exploration on the behavior of swarm intelligence between multiple teams, and cooperation between multiple agents due to their limited scalability. To alleviate this, we introduce GoBigger, a scalable platform for cooperative-competition multi-agent interactive simulation. GoBigger is an enhanced environment for the Agar-like game, enabling the simulation of multiple scales of agent intra-team cooperation and inter-team competition. Compared with existing multi-agent simulation environments, our platform supports multi-team games with more than two teams simultaneously, which dramatically expands the diversity of agent cooperation and competition, and can more effectively simulate the swarm intelligent agent behavior. Besides, in GoBigger, the cooperation between the agents in a team can lead to much higher performance. We offer a diverse set of challenging scenarios, built-in bots, and visualization tools for best practices in benchmarking. We evaluate several state-of-the-art algorithms on GoBigger and demonstrate the potential of the environment. We believe this platform can inspire various emerging research directions in MARL, swarm intelligence, and large-scale agent interactive learning. Both GoBigger and its related benchmark are open-sourced. More information could be found at https://github.com/opendilab/GoBigger.

Controlling agents remotely with deep reinforcement learning~(DRL) in the real world is yet to come. One crucial stepping stone is to devise RL algorithms that are robust in the face of dropped information from corrupted communication or malfunctioning sensors. Typical RL methods usually require considerable online interaction data that are costly and unsafe to collect in the real world. Furthermore, when applying to the frame dropping scenarios, they perform unsatisfactorily even with moderate drop rates. To address these issues, we propose Decision Transformer under Random Frame Dropping~(DeFog), an offline RL algorithm that enables agents to act robustly in frame dropping scenarios without online interaction. DeFog first randomly masks out data in the offline datasets and explicitly adds the time span of frame dropping as inputs. After that, a finetuning stage on the same offline dataset with a higher mask rate would further boost the performance. Empirical results show that DeFog outperforms strong baselines under severe frame drop rates like 90\%, while maintaining similar returns under non-frame-dropping conditions in the regular MuJoCo control benchmarks and the Atari environments. Our approach offers a robust and deployable solution for controlling agents in real-world environments with limited or unreliable data.

Face detection (FD) has achieved remarkable success over the past few years, yet, these leaps often arrive when consuming enormous computation costs. Moreover, when considering a realistic situation, i.e., building a lightweight face detector under a computation-scarce scenario, such heavy computation cost limits the application of the face detector. To remedy this, several pioneering works design tiny face detectors through off-the-shelf neural architecture search (NAS) technologies, which are usually applied to the classification task. Thus, the searched architectures are sub-optimal for the face detection task since some design criteria between detection and classification task are different. As a representative, the face detection backbone design needs to guarantee the stage-level detection ability while it is not required for the classification backbone. Furthermore, the detection backbone consumes a vast body of inference budgets in the whole detection framework. Considering the intrinsic design requirement and the virtual importance role of the face detection backbone, we thus ask a critical question: How to employ NAS to search FD-friendly backbone architecture? To cope with this question, we propose a distribution-dependent stage-aware ranking score (DDSAR-Score) to explicitly characterize the stage-level expressivity and identify the individual importance of each stage, thus satisfying the aforementioned design criterion of the FD backbone. Based on our proposed DDSAR-Score, we conduct comprehensive experiments on the challenging Wider Face benchmark dataset and achieve dominant performance across a wide range of compute regimes. In particular, compared to the tiniest face detector SCRFD-0.5GF, our method is +2.5 % better in Average Precision (AP) score when using the same amount of FLOPs. The code is avaliable at https://github.com/ly19965/FaceMaas/tree/master/face_project/face_detection/DamoFD.

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks. However, existing methods typically learn soft prompt vectors from scratch, and it has not been clear how to exploit the rich cross-task knowledge with prompt vectors in a multitask learning setting. We propose multitask prompt tuning (MPT), which first learns a single transferable prompt by distilling knowledge from multiple task-specific source prompts. We then learn multiplicative low rank updates to this shared prompt to efficiently adapt it to each downstream target task. Extensive experiments on 23 NLP datasets demonstrate that our proposed approach outperforms the state-of-the-art methods, including the full finetuning baseline in some cases, despite only tuning $0.035\%$ as many task-specific parameters.

Our brain can almost effortlessly decompose visual data streams into background and salient objects. Moreover, it can anticipate object motion and interactions, which are crucial abilities for conceptual planning and reasoning. Recent object reasoning datasets, such as CATER, have revealed fundamental shortcomings of current vision-based AI systems, particularly when targeting explicit object representations, object permanence, and object reasoning. Here we introduce a self-supervised LOCation and Identity tracking system (Loci), which excels on the CATER tracking challenge. Inspired by the dorsal and ventral pathways in the brain, Loci tackles the binding problem by processing separate, slot-wise encodings of 'what' and 'where'. Loci's predictive coding-like processing encourages active error minimization, such that individual slots tend to encode individual objects. Interactions between objects and object dynamics are processed in the disentangled latent space. Truncated backpropagation through time combined with forward eligibility accumulation significantly speeds up learning and improves memory efficiency. Besides exhibiting superior performance in current benchmarks, Loci effectively extracts objects from video streams and separates them into location and Gestalt components. We believe that this separation offers a representation that will facilitate effective planning and reasoning on conceptual levels.

We consider robust clustering problems in $\mathbb{R}^d$, specifically $k$-clustering problems (e.g., $k$-Median and $k$-Means) with $m$ \emph{outliers}, where the cost for a given center set $C \subset \mathbb{R}^d$ aggregates the distances from $C$ to all but the furthest $m$ data points, instead of all points as in classical clustering. We focus on the $\epsilon$-coreset for robust clustering, a small proxy of the dataset that preserves the clustering cost within $\epsilon$-relative error for all center sets. Our main result is an $\epsilon$-coreset of size $O(m + \mathrm{poly}(k \epsilon^{-1}))$ that can be constructed in near-linear time. This significantly improves previous results, which either suffers an exponential dependence on $(m + k)$ [Feldman and Schulman, SODA'12], or has a weaker bi-criteria guarantee [Huang et al., FOCS'18]. Furthermore, we show this dependence in $m$ is nearly-optimal, and the fact that it is isolated from other factors may be crucial for dealing with large number of outliers. We construct our coresets by adapting to the outlier setting a recent framework [Braverman et al., FOCS'22] which was designed for capacity-constrained clustering, overcoming a new challenge that the participating terms in the cost, particularly the excluded $m$ outlier points, are dependent on the center set $C$. We validate our coresets on various datasets, and we observe a superior size-accuracy tradeoff compared with popular baselines including uniform sampling and sensitivity sampling. We also achieve a significant speedup of existing approximation algorithms for robust clustering using our coresets.

Diffusion-based image translation guided by semantic texts or a single target image has enabled flexible style transfer which is not limited to the specific domains. Unfortunately, due to the stochastic nature of diffusion models, it is often difficult to maintain the original content of the image during the reverse diffusion. To address this, here we present a novel diffusion-based unsupervised image translation method, dubbed as DiffuseIT, using disentangled style and content representation. Specifically, inspired by the slicing Vision Transformer, we extract intermediate keys of multihead self attention layer from ViT model and used them as the content preservation loss. Then, an image guided style transfer is performed by matching the [CLS] classification token from the denoised samples and target image, whereas additional CLIP loss is used for the text-driven style transfer. To further accelerate the semantic change during the reverse diffusion, we also propose a novel semantic divergence loss and resampling strategy. Our experimental results show that the proposed method outperforms state-of-the-art baseline models in both text-guided and image-guided translation tasks.

Text classifiers have promising applications in high-stake tasks such as resume screening and content moderation. These classifiers must be fair and avoid discriminatory decisions by being invariant to perturbations of sensitive attributes such as gender or ethnicity. However, there is a gap between human intuition about these perturbations and the formal similarity specifications capturing them. While existing research has started to address this gap, current methods are based on hardcoded word replacements, resulting in specifications with limited expressivity or ones that fail to fully align with human intuition (e.g., in cases of asymmetric counterfactuals). This work proposes novel methods for bridging this gap by discovering expressive and intuitive individual fairness specifications. We show how to leverage unsupervised style transfer and GPT-3's zero-shot capabilities to automatically generate expressive candidate pairs of semantically similar sentences that differ along sensitive attributes. We then validate the generated pairs via an extensive crowdsourcing study, which confirms that a lot of these pairs align with human intuition about fairness in the context of toxicity classification. Finally, we show how limited amounts of human feedback can be leveraged to learn a similarity specification that can be used to train downstream fairness-aware models.

We introduce LilNetX, an end-to-end trainable technique for neural networks that enables learning models with specified accuracy-rate-computation trade-off. Prior works approach these problems one at a time and often require post-processing or multistage training which become less practical and do not scale very well for large datasets or architectures. Our method constructs a joint training objective that penalizes the self information of network parameters in a latent representation space to encourage small model size while also introducing priors to increase structured sparsity in the parameter space to reduce computation. When compared with existing state-of-the-art model compression methods, we achieve up to 50% smaller model size and 98% model sparsity on ResNet-20 on the CIFAR-10 dataset as well as 37% smaller model size and 71% structured sparsity on ResNet-50 trained on ImageNet while retaining the same accuracy as those methods. We show that the resulting sparsity can improve the inference time of the models by almost 1.8 times the dense ResNet-50 baseline model. Code is available at https://github.com/Sharath-girish/LilNetX.

The low-level sensory and motor signals in deep reinforcement learning, which exist in high-dimensional spaces such as image observations or motor torques, are inherently challenging to understand or utilize directly for downstream tasks. While sensory representations have been extensively studied, the representations of motor actions are still an area of active exploration. Our work reveals that a space containing meaningful action representations emerges when a multi-task policy network takes as inputs both states and task embeddings. Moderate constraints are added to improve its representation ability. Therefore, interpolated or composed embeddings can function as a high-level interface within this space, providing instructions to the agent for executing meaningful action sequences. Empirical results demonstrate that the proposed action representations are effective for intra-action interpolation and inter-action composition with limited or no additional learning. Furthermore, our approach exhibits superior task adaptation ability compared to strong baselines in Mujoco locomotion tasks. Our work sheds light on the promising direction of learning action representations for efficient, adaptable, and composable RL, forming the basis of abstract action planning and the understanding of motor signal space. Project page: https://sites.google.com/view/emergent-action-representation/

We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or masked image modeling, to convolutional networks (convnets): (i) convolution operation cannot handle irregular, randomly masked input images; (ii) the single-scale nature of BERT pre-training is inconsistent with convnet’s hierarchical structure. For (i), we treat unmasked pixels as sparse voxels of 3D point clouds and use sparse convolution to encode. This is the first use of sparse convolution for 2D masked modeling. For (ii), we develop a hierarchical decoder to reconstruct images from multi-scale encoded features. Our method, called Sparse masKed modeling (SparK), is general: it can be used directly on any convolutional model without backbone modifications. We validate it on both classical (ResNet) and modern (ConvNeXt) models: on three downstream tasks, it surpasses both state-of-the-art contrastive learning and transformer-based masked modeling by similarly large margins (around +1.0%). The improvements on object detection and instance segmentation are more significant (up to +3.5%), validating the strong transferability of features learned. We also find SparK’s favorable scaling behavior by observing more gains on larger networks. All of these findings support the promising future of generative pre-training on convnets. Both codes and pre-trained models have been released at https://github.com/keyu-tian/SparK.

Analogical reasoning is fundamental to human cognition and holds an important place in various fields. However, previous studies mainly focus on single-modal analogical reasoning and ignore taking advantage of structure knowledge. Notably, the research in cognitive psychology has demonstrated that information from multimodal sources always brings more powerful cognitive transfer than single modality sources. To this end, we introduce the new task of multimodal analogical reasoning over knowledge graphs, which requires multimodal reasoning ability with the help of background knowledge. Specifically, we construct a Multimodal Analogical Reasoning dataSet (MARS) and a multimodal knowledge graph MarKG. We evaluate with multimodal knowledge graph embedding and pre-trained Transformer baselines, illustrating the potential challenges of the proposed task. We further propose a novel model-agnostic Multimodal analogical reasoning framework with Transformer (MarT) motivated by the structure mapping theory, which can obtain better performance. We hope our work can deliver benefits and inspire future research. Code and datasets are available in https://github.com/zjunlp/MKG_Analogy.

Skip connections and normalisation layers form two standard architectural components that are ubiquitous for the training of Deep Neural Networks (DNNs), but whose precise roles are poorly understood. Recent approaches such as Deep Kernel Shaping have made progress towards reducing our reliance on them, using insights from wide NN kernel theory to improve signal propagation in vanilla DNNs (which we define as networks without skips or normalisation). However, these approaches are incompatible with the self-attention layers present in transformers, whose kernels are intrinsically more complicated to analyse and control. And so the question remains: \emph{is it possible to train deep vanilla transformers?} We answer this question in the affirmative by designing several approaches that use combinations of parameter initialisations, bias matrices and location-dependent rescaling to achieve faithful signal propagation in vanilla transformers. Our methods address various intricacies specific to signal propagation in transformers, including the interaction with positional encoding and causal masking. In experiments on WikiText-103 and C4, our approaches enable deep transformers without normalisation to train at speeds matching their standard counterparts, and deep vanilla transformers to reach the same performance as standard ones after about 5 times more iterations.

Oriented object detection emerges in many applications from aerial images to autonomous driving, while many existing detection benchmarks are annotated with horizontal bounding box only which is also less costive than fine-grained rotated box, leading to a gap between the readily available training corpus and the rising demand for oriented object detection. This paper proposes a simple yet effective oriented object detection approach called H2RBox merely using horizontal box annotation for weakly-supervised training, which closes the above gap and shows competitive performance even against those trained with rotated boxes. The cores of our method are weakly- and self-supervised learning, which predicts the angle of the object by learning the consistency of two different views. To our best knowledge, H2RBox is the first horizontal box annotation-based oriented object detector. Compared to an alternative i.e. horizontal box-supervised instance segmentation with our post adaption to oriented object detection, our approach is not susceptible to the prediction quality of mask and can perform more robustly in complex scenes containing a large number of dense objects and outliers. Experimental results show that H2RBox has significant performance and speed advantages over horizontal box-supervised instance segmentation methods, as well as lower memory requirements. While compared to rotated box-supervised oriented object detectors, our method shows very close performance and speed. The source code is available at PyTorch-based \href{https://github.com/yangxue0827/h2rbox-mmrotate}{MMRotate} and Jittor-based \href{https://github.com/yangxue0827/h2rbox-jittor}{JDet}.

We aim to train accurate denoising networks for smartphone/digital cameras from single noisy images. Downscaling is commonly used as a practical denoiser for low-resolution images. Based on this processing, we found that the pixel variance of the natural images is more robust to downscaling than the pixel variance of the camera noises. Intuitively, downscaling easily removes high-frequency noises than natural textures. To utilize this property, we can adopt noisy/clean image synthesis at low-resolution to train camera denoisers. On this basis, we propose a new solution pipeline -- NERDS that estimates camera noises and synthesizes noisy-clean image pairs from only noisy images. In particular, it first models the noise in raw-sensor images as a Poisson-Gaussian distribution, then estimates the noise parameters using the difference of pixel variances by downscaling. We formulate the noise estimation as a gradient-descent-based optimization problem through a reparametrization trick. We further introduce a new Image Signal Processor (ISP) estimation method that enables denoiser training in a human-readable RGB space by transforming the synthetic raw images to the style of a given RGB noisy image. The noise and ISP estimations utilize rich augmentation to synthesize image pairs for denoiser training. Experiments show that our NERDS can accurately train CNN-based denoisers (e.g., DnCNN, ResNet-style network) outperforming previous noise-synthesis-based and self-supervision-based denoisers in real datasets.