ICLR 2023 论文列表

Understanding dynamics from visual observations is a challenging problem that requires disentangling individual objects from the scene and learning their interactions. While recent object-centric models can successfully decompose a scene into objects, modeling their dynamics effectively still remains a challenge. We address this problem by introducing SlotFormer -- a Transformer-based autoregressive model operating on learned object-centric representations. Given a video clip, our approach reasons over object features to model spatio-temporal relationships and predicts accurate future object states. In this paper, we successfully apply SlotFormer to perform video prediction on datasets with complex object interactions. Moreover, the unsupervised SlotFormer's dynamics model can be used to improve the performance on supervised downstream tasks, such as Visual Question Answering (VQA), and goal-conditioned planning. Compared to past works on dynamics modeling, our method achieves significantly better long-term synthesis of object dynamics, while retaining high quality visual generation. Besides, SlotFormer enables VQA models to reason about the future without object-level labels, even outperforming counterparts that use ground-truth annotations. Finally, we show its ability to serve as a world model for model-based planning, which is competitive with methods designed specifically for such tasks.

Existing federated learning paradigms usually extensively exchange distributed models, rather than original data, at a central solver to achieve a more powerful model. However, this would incur severe communication burden between a server and multiple clients especially when data distributions are heterogeneous. As a result, current federated learning methods often require plenty of communication rounds in training. Unlike existing paradigms, we introduce an alternative perspective to significantly decrease the federate learning communication cost without leaking original data. In this work, we first present a meta knowledge representation method that extracts meta knowledge from distributed clients. The extracted meta knowledge encodes essential information that can be used to improve the current model. As the training progresses, the contributions of the same training samples to a federated model should also vary. Thus, we introduce a dynamic weight assignment mechanism that enables informative samples to contribute adaptively to the current model update. Then, informative meta knowledge from all active clients is sent to the server for model update. Training model on the combined meta knowledge that is regarded as a condense form of original data can significantly mitigate the heterogeneity issues. Moreover, to further ameliorate data heterogeneity, we also exchange meta knowledge among clients as conditional initialisation for meta knowledge extraction. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method. Remarkably, our method outperforms the state-of-the-art by a large margin (from $74.07\%$ to $92.95\%$) on MNIST with a restricted communication budget (\textit{i.e.}, 10 rounds).

Deep generative models parametrized up to a normalizing constant (e.g. energy-based models) are difficult to train by maximizing the likelihood of the data because the likelihood and/or gradients thereof cannot be explicitly or efficiently written down. Score matching is a training method, whereby instead of fitting the likelihood $\log p(x)$ for the training data, we instead fit the score function $\nabla_x \log p(x)$ --- obviating the need to evaluate the partition function. Though this estimator is known to be consistent, its unclear whether (and when) its statistical efficiency is comparable to that of maximum likelihood --- which is known to be (asymptotically) optimal. We initiate this line of inquiry in this paper, and show a tight connection between statistical efficiency of score matching and the isoperimetric properties of the distribution being estimated --- i.e. the Poincar\'e, log-Sobolev and isoperimetric constant --- quantities which govern the mixing time of Markov processes like Langevin dynamics. Roughly, we show that the score matching estimator is statistically comparable to the maximum likelihood when the distribution has a small isoperimetric constant. Conversely, if the distribution has a large isoperimetric constant --- even for simple families of distributions like exponential families with rich enough sufficient statistics --- score matching will be substantially less efficient than maximum likelihood. We suitably formalize these results both in the finite sample regime, and in the asymptotic regime. Finally, we identify a direct parallel in the discrete setting, where we connect the statistical properties of pseudolikelihood estimation with approximate tensorization of entropy and the Glauber dynamics.

Learning from large amounts of unsupervised data and a small amount of supervision is an important open problem in computer vision. We propose a new semi-supervised learning method, Semantic Positives via Pseudo-Labels (SEMPPL), that combines labelled and unlabelled data to learn informative representations. Our method extends self-supervised contrastive learning—where representations are shaped by distinguishing whether two samples represent the same underlying datum (positives) or not (negatives)—with a novel approach to selecting positives. To enrich the set of positives, we leverage the few existing ground-truth labels to predict the missing ones through a k-nearest neighbors classifier by using the learned embeddings of the labelled data. We thus extend the set of positives with datapoints having the same pseudo-label and call these semantic positives. We jointly learn the representation and predict bootstrapped pseudo-labels. This creates a reinforcing cycle. Strong initial representations enable better pseudo-label predictions which then improve the selection of semantic positives and lead to even better representations. SEMPPL outperforms competing semi-supervised methods setting new state-of-the-art performance of 76% and 68.5% top-1accuracy when using a ResNet-50 and training on 10% and 1% of labels on ImageNet, respectively. Furthermore, when using selective kernels, SEMPPL significantly outperforms previous state-of-the-art achieving 72.3% and 78.3% top-1accuracy on ImageNet with 1% and 10% labels, respectively, which improves absolute +7.8% and +6.2% over previous work. SEMPPL also exhibits state-of-the-art performance over larger ResNet models as well as strong robustness, out-of-distribution and transfer performance. We release the checkpoints and the evaluation code at https://github.com/deepmind/semppl.

Training large, deep neural networks to convergence can be prohibitively expensive. As a result, often only a small selection of popular, dense models are reused across different contexts and tasks. Increasingly, sparsely activated models, which seek to decouple model size from computation costs, are becoming an attractive alternative to dense models. Although more efficient in terms of quality and computation cost, sparse models remain data-hungry and costly to train from scratch in the large scale regime. In this work, we propose sparse upcycling -- a simple way to reuse sunk training costs by initializing a sparsely activated Mixture-of-Experts model from a dense checkpoint. We show that sparsely upcycled T5 Base, Large, and XL language models and Vision Transformer Base and Large models, respectively, significantly outperform their dense counterparts on SuperGLUE and ImageNet, using only ~50% of the initial dense pretraining sunk cost. The upcycled models also outperform sparse models trained from scratch on 100% of the initial dense pretraining computation budget.

Fast and accurate adaptation of automatic speech recognition (ASR) systems using only text data in the target domain is a problem of long-standing practical relevance. Text-only adaptation was easy in traditional cascaded ASR systems with completely decoupled acoustic and language models. Recently, the RNNTransducer (RNN-T) has emerged as a default ASR model because of its high accuracy, low latency, and capability of supporting streaming input. However text-only adaptation of the RNN-T model is significantly more challenging due to its tight integration of acoustic and language models and end-to-end training. Existing recent approaches for text-only adaptation of RNN-Ts, either entail significant modification to the network or introduce high latency during decoding. We propose a new approach (TOLSTOI) that imputes speech representations internal to a baseline RNN-T, starting from text-only inputs, and performs in-situ adaptation that results in higher adaptation accuracy without any runtime overheads during decoding. Our imputation model is a function of the labeled data and trained parameters of the ASR model, and that we show, is more effective in controlling catastrophic forgetting compared to existing methods. We establish the effectiveness of TOLSTOI using three target domains and two ASR models of varying complexity. We yield up to 35% relative reduction in word error rate with text-only adaptation while forgetting the least compared to existing adaptation approaches. Our method is easy to implement and can be harnessed on existing RNN-T models without requiring ASR model training from scratch.

Serving a GNN model online is challenging --- in many applications when testing nodes are connected to training nodes, one has to propagate information from training nodes to testing nodes to achieve the best performance, and storing the whole training set (including training graph and node features) during inference stage is prohibitive for large-scale problems. In this paper, we study graph compression to reduce the storage requirement for GNN in serving. Given a GNN model to be served, we propose to construct a compressed graph with a smaller number of nodes. In serving time, one just needs to replace the original training set graph by this compressed graph, without the need of changing the actual GNN model and the forward pass. We carefully analyze the error in the forward pass and derive simple ways to construct the compressed graph to minimize the approximation error. Experimental results on semi-supervised node classification demonstrate that the proposed method can significantly reduce the serving space requirement for GNN inference.

Recently, RL has shown its strong ability for visually complex tasks. However, it suffers from the low sample efficiency and poor generalization ability, which prevent RL from being useful in real-world scenarios. Inspired by the huge success of unsupervised pre-training methods on language and vision domains, we propose to improve the sample efficiency via a novel pre-training method for model-based RL. Instead of using pre-recorded agent trajectories that come with their own actions, we consider the setting where the pre-training data are action-free videos, which are more common and available in the real world. We introduce a two-phase training pipeline as follows: for the pre-training phase, we implicitly extract the hidden action embedding from videos and pre-train the visual representation and the environment dynamics network through a novel \Changes{forward-inverse} cycle consistency \Changes{(FICC)} objective based on vector quantization; for down-stream tasks, we finetune with small amount of task data based on the learned models. Our framework can significantly improve the sample efficiency on Atari Games with data of only one hour of game playing. We achieve 118.4\% mean human performance and 36.0\% median performance with only 50k environment steps, which is 85.6\% and 65.1\% better than the scratch EfficientZero model. We believe such pre-training approach can provide an option for solving real-world RL problems. The code is available at \url{https://github.com/YeWR/FICC.git}.

Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. Ideally, the distribution of the data points in the latent space should depend only on the task, the data, the loss, and other architecture-specific constraints. However, factors such as the random weights initialization, training hyperparameters, or other sources of randomness in the training phase may induce incoherent latent spaces that hinder any form of reuse. Nevertheless, we empirically observe that, under the same data and modeling choices, the angles between the encodings within distinct latent spaces do not change. In this work, we propose the latent similarity between each sample and a fixed set of anchors as an alternative data representation, demonstrating that it can enforce the desired invariances without any additional training. We show how neural architectures can leverage these relative representations to guarantee, in practice, invariance to latent isometries and rescalings, effectively enabling latent space communication: from zero-shot model stitching to latent space comparison between diverse settings. We extensively validate the generalization capability of our approach on different datasets, spanning various modalities (images, text, graphs), tasks (e.g., classification, reconstruction) and architectures (e.g., CNNs, GCNs, transformers).

Complex Query Answering (CQA) over Knowledge Graphs (KGs) has attracted a lot of attention to potentially support many applications. Given that KGs are usually incomplete, neural models are proposed to answer the logical queries by parameterizing set operators with complex neural networks. However, such methods usually train neural set operators with a large number of entity and relation embeddings from the zero, where whether and how the embeddings or the neural set operators contribute to the performance remains not clear. In this paper, we propose a simple framework for complex query answering that decomposes the KG embeddings from neural set operators. We propose to represent the complex queries into the query graph. On top of the query graph, we propose the Logical Message Passing Neural Network (LMPNN) that connects the local one-hop inferences on atomic formulas to the global logical reasoning for complex query answering. We leverage existing effective KG embeddings to conduct one-hop inferences on atomic formulas, the results of which are regarded as the messages passed in LMPNN. The reasoning process over the overall logical formulas is turned into the forward pass of LMPNN that incrementally aggregates local information to finally predict the answers' embeddings. The complex logical inference across different types of queries will then be learned from training examples based on the LMPNN architecture. Theoretically, our query-graph represenation is more general than the prevailing operator-tree formulation, so our approach applies to a broader range of complex KG queries. Empirically, our approach yields the new state-of-the-art neural CQA model. Our research bridges the gap between complex KG query answering tasks and the long-standing achievements of knowledge graph representation learning. Our implementation can be found at https://github.com/HKUST-KnowComp/LMPNN.

AlphaZero-type algorithms may stop improving on single-player tasks in case the value network guiding the tree search is unable to approximate the outcome of an episode sufficiently well. One technique to address this problem is transforming the single-player task through self-competition. The main idea is to compute a scalar baseline from the agent’s historical performances and to reshape an episode’s reward into a binary output, indicating whether the baseline has been exceeded or not. However, this baseline only carries limited information for the agent about strategies how to improve. We leverage the idea of self-competition and directly incorporate a historical policy into the planning process instead of its scalar performance. Based on the recently introduced Gumbel AlphaZero (GAZ), we propose our algorithm GAZ ‘Play-to-Plan’ (GAZ PTP), in which the agent learns to find strong trajectories by planning against possible strategies of its past self. We show the effectiveness of our approach in two well-known combinatorial optimization problems, the Traveling Salesman Problem and the Job-Shop Scheduling Problem. With only half of the simulation budget for search, GAZ PTP consistently outperforms all selected single-player variants of GAZ.

Experience replay, which stores transitions in a replay memory for repeated use, plays an important role of improving sample efficiency in reinforcement learning. Existing techniques such as reweighted sampling, episodic learning and reverse sweep update further process the information in the replay memory to make experience replay more efficient. In this work, we further exploit the information in the replay memory by treating it as an empirical \emph{Replay Memory MDP (RM-MDP)}. By solving it with dynamic programming, we learn a conservative value estimate that \emph{only} considers transitions observed in the replay memory. Both value and policy regularizers based on this conservative estimate are developed and integrated with model-free learning algorithms. We design the metric \textit{memory density} to measure the quality of RM-MDP. Our empirical studies quantitatively find a strong correlation between performance improvement and memory density. Our method combines \emph{Conservative Estimation with Experience Replay (CEER)}, improving sample efficiency by a large margin, especially when the memory density is high. Even when the memory density is low, such a conservative estimate can still help to avoid suicidal actions and thereby improve performance.

Unsupervised text-to-speech (TTS) aims to train TTS models for a specific language without any paired speech-text training data in that language. Existing methods either use speech and corresponding pseudo text generated by an unsupervised automatic speech recognition (ASR) model as training data, or employ the back-translation technique. Though effective, they suffer from low robustness to low-quality data and heavy dependence on the lexicon of a language that is sometimes unavailable, leading to difficulty in convergence, especially in low-resource language scenarios. In this work, we introduce a bag of tricks to enable effective unsupervised TTS. Specifically, 1) we carefully design a voice conversion model to normalize the variable and noisy information in the low-quality speech data while preserving the pronunciation information; 2) we employ the non-autoregressive TTS model to overcome the robustness issue; and 3) we explore several tricks applied in back-translation, including curriculum learning, length augmentation and auxiliary supervised loss to stabilize the back-translation and improve its effectiveness. Through experiments, it has been demonstrated that our method achieves better intelligibility and audio quality than all previous methods, and that these tricks are very essential to the performance gain.

Recent Language Models (LMs) achieve breakthrough performance in code generation when trained on human-authored problems, even solving some competitive-programming problems. Self-play has proven useful in games such as Go, and thus it is natural to ask whether LMs can generate their own instructive programming problems to improve their performance. We show that it is possible for an LM to synthesize programming problems and solutions, which are filtered for correctness by a Python interpreter. The LM’s performance is then seen to improve when it is fine-tuned on its own synthetic problems and verified solutions; thus the model “improves itself” using the Python interpreter. Problems are specified formally as programming puzzles [Schuster et al. , 2021], a code-based problem format where solutions can easily be verified for correctness by execution. In experiments on publicly-available LMs, test accuracy more than doubles. This work demonstrates the potential for code LMs, with an interpreter, to generate instructive problems and improve their own performance.

The transferability of adversarial perturbations between image models has been extensively studied. In this case, an attack is generated from a known surrogate \eg, the ImageNet trained model, and transferred to change the decision of an unknown (black-box) model trained on an image dataset. However, attacks generated from image models do not capture the dynamic nature of a moving object or a changing scene due to a lack of temporal cues within image models. This leads to reduced transferability of adversarial attacks from representation-enriched \emph{image} models such as Supervised Vision Transformers (ViTs), Self-supervised ViTs (\eg, DINO), and Vision-language models (\eg, CLIP) to black-box \emph{video} models. In this work, we induce dynamic cues within the image models without sacrificing their original performance on images. To this end, we optimize \emph{temporal prompts} through frozen image models to capture motion dynamics. Our temporal prompts are the result of a learnable transformation that allows optimizing for temporal gradients during an adversarial attack to fool the motion dynamics. Specifically, we introduce spatial (image) and temporal (video) cues within the same source model through task-specific prompts. Attacking such prompts maximizes the adversarial transferability from image-to-video and image-to-image models using the attacks designed for image models. As an example, an iterative attack launched from image model Deit-B with temporal prompts reduces generalization (top1 \% accuracy) of a video model by 35\% on Kinetics-400. Our approach also improves adversarial transferability to image models by 9\% on ImageNet w.r.t the current state-of-the-art approach. Our attack results indicate that the attacker does not need specialized architectures, \eg, divided space-time attention, 3D convolutions, or multi-view convolution networks for different data modalities. Image models are effective surrogates to optimize an adversarial attack to fool black-box models in a changing environment over time. Code is available at \url{https://bit.ly/3Xd9gRQ}

The pursuit of long-term fairness involves the interplay between decision-making and the underlying data generating process. In this paper, through causal modeling with a directed acyclic graph (DAG) on the decision-distribution interplay, we investigate the possibility of achieving long-term fairness from a dynamic perspective. We propose Tier Balancing, a technically more challenging but more natural notion to achieve in the context of long-term, dynamic fairness analysis. Different from previous fairness notions that are defined purely on observed variables, our notion goes one step further, capturing behind-the-scenes situation changes on the unobserved latent causal factors that directly carry out the influence from the current decision to the future data distribution. Under the specified dynamics, we prove that in general one cannot achieve the long-term fairness goal only through one-step interventions. Furthermore, in the effort of approaching long-term fairness, we consider the mission of "getting closer to" the long-term fairness goal and present possibility and impossibility results accordingly.

Data heterogeneity is one of the most challenging issues in federated learning, which motivates a variety of approaches to learn personalized models for participating clients. One such approach in deep neural networks based tasks is employing a shared feature representation and learning a customized classifier head for each client. However, previous works do not utilize the global knowledge during local representation learning and also neglect the fine-grained collaboration between local classifier heads, which limits the model generalization ability. In this work, we conduct explicit local-global feature alignment by leveraging global semantic knowledge for learning a better representation. Moreover, we quantify the benefit of classifier combination for each client as a function of the combining weights and derive an optimization problem for estimating optimal weights. Finally, extensive evaluation results on benchmark datasets with various heterogeneous data scenarios demonstrate the effectiveness of our proposed method.

There are sequence generation tasks where the best order to generate the target sequence is not left-to-right. For example, an answer to the Sudoku game, a structured code like s-expression, and even a logical natural language answer where the analysis may be generated after the decision. We define the target sequences of those tasks as complex sequences. Obviously, a complex sequence should be constructed with multiple logical steps, and has dependencies among each part of itself (e.g. decisions depend on analyses). It's a great challenge for the classic left-to-right autoregressive generation system to generate complex sequences. Current approaches improve one-pass left-to-right generation on NLG tasks by generating different heuristic intermediate sequences in multiple stages. However, for complex sequences, the heuristic rules to break down them may hurt performance, and increase additional exposure bias. To tackle these challenges, we propose a PLM-friendly autoregressive self-boost refinement framework, CASR. When training, CASR inputs the predictions generated by the model itself at the previous refinement step (instead of those produced by heuristic rules). To find an optimal design, we also discuss model architecture, parameter efficiency and initialization strategy. By evaluating CASR on Sudoku, WebQSP, MTOP and KVRET through controlled experiments and empirical studies, we find that CASR produces high-quality outputs. CASR also improves Accuracy on Sudoku (70.93% --> 97.28%) and achieves state-of-the-art performance on KVRET with Micro F1 score (67.88% --> 70.00%).

We present Analogical Networks, a model that segments 3D object scenes with analogical reasoning: instead of mapping a scene to part segments directly, our model first retrieves related scenes from memory and their corresponding part structures, and then predicts analogous part structures in the input object 3D point cloud, via an end-to-end learnable modulation mechanism. By conditioning on more than one retrieved memories, compositions of structures are predicted, that mix and match parts across the retrieved memories. One-shot, few-shot or many-shot learning are treated uniformly in Analogical Networks, by conditioning on the appropriate set of memories, whether taken from a single, few or many memory exemplars, and inferring analogous parses. We show Analogical Networks are competitive with state-of-the-art 3D segmentation transformer in many-shot settings and outperform them and existing paradigms of meta-learning and few-shot learning in few-shot scenarios. Our model successfully parses instances of novel object categories simply by expanding its memory, without any weight updates.