| Total: 1213
The great success of deep learning heavily relies on increasingly larger training data, which comes at a price of huge computational and infrastructural costs. This poses crucial questions that, do all training data contribute to model's performance? How much does each individual training sample or a sub-training-set affect the model's generalization, and how to construct the smallest subset from the entire training data as a proxy training set without significantly sacrificing the model's performance? To answer these, we propose dataset pruning, an optimization-based sample selection method that can (1) examine the influence of removing a particular set of training samples on model's generalization ability with theoretical guarantee, and (2) construct the smallest subset of training data that yields strictly constrained generalization gap. The empirically observed generalization gap of dataset pruning is substantially consistent with our theoretical expectations. Furthermore, the proposed method prunes 40% training examples on the CIFAR-10 dataset, halves the convergence time with only 1.3% test accuracy decrease, which is superior to previous score-based sample selection methods.
Graph neural networks (GNNs), as the de-facto model class for representation learning on graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional message passing layers to allow features to flow across nodes. While conventional wisdom commonly attributes the success of GNNs to their advanced expressivity, we conjecture that this is not the main cause of GNNs' superiority in node-level prediction tasks. This paper pinpoints the major source of GNNs' performance gain to their intrinsic generalization capability, by introducing an intermediate model class dubbed as P(ropagational)MLP, which is identical to standard MLP in training, but then adopts GNN's architecture in testing. Intriguingly, we observe that PMLPs consistently perform on par with (or even exceed) their GNN counterparts, while being much more efficient in training.This finding provides a new perspective for understanding the learning behavior of GNNs, and can be used as an analytic tool for dissecting various GNN-related research problems including expressivity, generalization, over-smoothing and heterophily. As an initial step to analyze PMLP, we show its essential difference to MLP at infinite-width limit lies in the NTK feature map in the post-training stage. Moreover, through extrapolation analysis (i.e., generalization under distribution shifts), we find that though most GNNs and their PMLP counterparts cannot extrapolate non-linear functions for extreme out-of-distribution data, they have greater potential to generalize to testing data near the training data support as natural advantages of the GNN architecture used for inference.
The unprecedented rate at which the sizes of machine learning (ML) models are growing necessitates novel approaches to enable efficient and scalable solutions. We contribute to this line of work by studying a novel version of the Budgeted Correlation Clustering problem (\bcc) where along with a limited number of queries to an expensive oracle for node similarities (e.g. a large ML model), we have unlimited access to a cheaper but less accurate second oracle. Our formulation is inspired by many practical scenarios where coarse approximations of the expensive similarity metric can be efficiently obtained via weaker models. We develop a theoretically motivated algorithm in this setting that leverages the cheap oracle to judiciously query the strong oracle while maintaining high clustering quality. We empirically demonstrate gains in query minimization and clustering metrics on a variety of datasets with diverse strong and cheap oracles. Most notably, we demonstrate a practical application in text clustering based on expensive cross-attention language models by showing that cheaper (but weaker) embedding-based models can be leveraged to substantially reduce the number of inference calls to the former.
Data augmentations are effective in improving the invariance of learning machines. We argue that the core challenge of data augmentations lies in designing data transformations that preserve labels. This is relatively straightforward for images, but much more challenging for graphs. In this work, we propose GraphAug, a novel automated data augmentation method aiming at computing label-invariant augmentations for graph classification. Instead of using uniform transformations as in existing studies, GraphAug uses an automated augmentation model to avoid compromising critical label-related information of the graph, thereby producing label-invariant augmentations at most times. To ensure label-invariance, we develop a training method based on reinforcement learning to maximize an estimated label-invariance probability. Experiments show that GraphAug outperforms previous graph augmentation methods on various graph classification tasks.
In this work, we attempt to bridge the two fields of finite-agent and infinite-agent games, by studying how the optimal policies of agents evolve with the number of agents (population size) in mean-field games, an agent-centric perspective in contrast to the existing works focusing typically on the convergence of the empirical distribution of the population. To this end, the premise is to obtain the optimal policies of a set of finite-agent games with different population sizes. However, either deriving the closed-form solution for each game is theoretically intractable, training a distinct policy for each game is computationally intensive, or directly applying the policy trained in a game to other games is sub-optimal. We address these challenges through the \textbf{P}opulation-size-\textbf{A}ware \textbf{P}olicy \textbf{O}ptimization (PAPO). Our contributions are three-fold. First, to efficiently generate efficient policies for games with different population sizes, we propose PAPO, which unifies two natural options (augmentation and hypernetwork) and achieves significantly better performance. PAPO consists of three components: i) the population-size encoding which transforms the original value of population size to an equivalent encoding to avoid training collapse, ii) a hypernetwork to generate a distinct policy for each game conditioned on the population size, and iii) the population size as an additional input to the generated policy. Next, we construct a multi-task-based training procedure to efficiently train the neural networks of PAPO by sampling data from multiple games with different population sizes. Finally, extensive experiments on multiple environments show the significant superiority of PAPO over baselines, and the analysis of the evolution of the generated policies further deepens our understanding of the two fields of finite-agent and infinite-agent games.
Representation learning on semi-structured data, e.g., graphs, has become a central problem in deep learning community as relational structures are pervasive in real situations and induce data inter-dependence that hinders trivial adaptation of existing approaches in other domains where the inputs are assumed to be i.i.d. sampled. However, current models in this regime mostly focus on improving testing performance of in-distribution data and largely ignores the potential risk w.r.t. out-of-distribution (OOD) testing samples that may cause negative outcome if the model is overconfident in prediction on them. In this paper, we identify a provably effective OOD discriminator based on an energy function directly extracted from a graph neural network trained with standard supervised classification loss. This paves a way for a simple and efficient OOD detection model for GNN-based semi-supervised learning on graphs, which we call GNN-Safe. It also has nice theoretical properties that guarantee an overall distinguishable margin between the detection scores for in-distribution and OOD samples, which, more critically, can be further strengthened by a non-learning-based structured propagation scheme. Extensive experiments over five real-world datasets validate the practical efficacy of the proposed model for detecting various OOD instances that are inter-connected in a graph with up to 17.0% improvement on average AUROC over competitive peer models and without sacrificing in-distribution testing accuracy.
Despite the recent success of deep learning for time series forecasting, these methods are not scalable for many real-world applications where data arrives sequentially. Training deep neural forecasters on the fly is notoriously challenging because of their limited ability to adapt to non-stationary environments and remember old knowledge. We argue that the fast adaptation capability of deep neural networks is critical and successful solutions require handling changes to both new and recurring patterns effectively. In this work, inspired by the Complementary Learning Systems (CLS) theory, we propose Fast and Slow learning Network (FSNet) as a novel framework to address the challenges of online forecasting. Particularly, FSNet improves the slowly-learned backbone by dynamically balancing fast adaptation to recent changes and retrieving similar old knowledge. FSNet achieves this mechanism via an interaction between two novel complementary components: (i) a per-layer adapter to support fast learning from individual layers, and (ii) an associative memory to support remembering, updating, and recalling repeating events. Extensive experiments on real and synthetic datasets validate FSNet's efficacy and robustness to both new and recurring patterns. Our code is publicly available at: \url{https://github.com/salesforce/fsnet/}.
Active Anomaly Discovery (AAD) is flourishing in the anomaly detection research area, which aims to incorporate analysts’ feedback into unsupervised anomaly detectors. However, existing AAD approaches usually prioritize the samples with the highest anomaly scores for user labeling, which hinders the exploration of anomalies that were initially ranked lower. Besides, most existing AAD approaches are specially tailored for a certain unsupervised detector, making it difficult to extend to other detection models. To tackle these problems, we propose a lightweight, model-agnostic and diversity-aware AAD method, named LMADA. In LMADA, we design a diversity-aware sample selector powered by Determinantal Point Process (DPP). It considers the diversity of samples in addition to their anomaly scores for feedback querying. Furthermore, we propose a model-agnostic tuner. It approximates diverse unsupervised detectors with a unified proxy model, based on which the feedback information is incorporated by a lightweight non-linear representation adjuster. Through extensive experiments on 8 public datasets, LMADA achieved 74% F1-Score improvement on average, outperforming other comparative AAD approaches. Besides, LMADA can also achieve significant performance boosting under any unsupervised detectors.
Learning logical rules is critical to improving reasoning in KGs. This is due to their ability to provide logical and interpretable explanations when used for predictions, as well as their ability to generalize to other tasks, domains, and data. While recent methods have been proposed to learn logical rules, the majority of these methods are either restricted by their computational complexity and can not handle the large search space of large-scale KGs, or show poor generalization when exposed to data outside the training set. In this paper, we propose an end-to-end neural model for learning compositional logical rules called NCRL. NCRL detects the best compositional structure of a rule body, and breaks it into small compositions in order to infer the rule head. By recurrently merging compositions in the rule body with a recurrent attention unit, NCRL finally predicts a single rule head. Experimental results show that NCRL learns high-quality rules, as well as being generalizable. Specifically, we show that NCRL is scalable, efficient, and yields state-of-the-art results for knowledge graph completion on large-scale KGs. Moreover, we test NCRL for systematic generalization by learning to reason on small-scale observed graphs and evaluating on larger unseen ones.
The robustness of machine learning algorithms to distributions shift is primarily discussed in the context of supervised learning (SL). As such, there is a lack of insight on the robustness of the representations learned from unsupervised methods, such as self-supervised learning (SSL) and auto-encoder based algorithms (AE), to distribution shift. We posit that the input-driven objectives of unsupervised algorithms lead to representations that are more robust to distribution shift than the target-driven objective of SL. We verify this by extensively evaluating the performance of SSL and AE on both synthetic and realistic distribution shift datasets. Following observations that the linear layer used for classification itself can be susceptible to spurious correlations, we evaluate the representations using a linearhead trained on a small amount of out-of-distribution (OOD) data, to isolate the robustness of the learned representations from that of the linear head. We also develop “controllable” versions of existing realistic domain generalisation datasets with adjustable degrees of distribution shifts. This allows us to study the robustness of different learning algorithms under versatile yet realistic distribution shiftconditions. Our experiments show that representations learned from unsupervised learning algorithms generalise better than SL under a wide variety of extreme as well as realistic distribution shifts.
This paper proposes a simple method to distill and detect backdoor patterns within an image: \emph{Cognitive Distillation} (CD). The idea is to extract the ``minimal essence" from an input image responsible for the model's prediction. CD optimizes an input mask to extract a small pattern from the input image that can lead to the same model output (i.e., logits or deep features). The extracted pattern can help understand the cognitive mechanism of a model on clean vs. backdoor images and is thus called a \emph{Cognitive Pattern} (CP). Using CD and the distilled CPs, we uncover an interesting phenomenon of backdoor attacks: despite the various forms and sizes of trigger patterns used by different attacks, the CPs of backdoor samples are all surprisingly and suspiciously small. One thus can leverage the learned mask to detect and remove backdoor examples from poisoned training datasets. We conduct extensive experiments to show that CD can robustly detect a wide range of advanced backdoor attacks.We also show that CD can potentially be applied to help detect potential biases from face datasets.Code is available at https://github.com/HanxunH/CognitiveDistillation.
We present a deep learning approach for repairing sequential circuits against formal specifications given in linear-time temporal logic (LTL). Given a defective circuit and its formal specification, we train Transformer models to output circuits that satisfy the corresponding specification. We propose a separated hierarchical Transformer for multimodal representation learning of the formal specification and the circuit. We introduce a data generation algorithm that enables generalization to more complex specifications and out-of-distribution datasets. In addition, our proposed repair mechanism significantly improves the automated synthesis of circuits from LTL specifications with Transformers. It improves the state-of-the-art by $6.8$ percentage points on held-out instances and $11.8$ percentage points on an out-of-distribution dataset from the annual reactive synthesis competition.
Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the capacity gap between students and teachers becomes larger, existing KD methods fail to achieve better results. Our work shows that the 'prior knowledge' is vital to KD, especially when applying large teachers. Particularly, we propose the dynamic prior knowledge (DPK), which integrates part of teacher's features as the prior knowledge before the feature distillation. This means that our method also takes the teacher's feature as `input', not just `target'. Besides, we dynamically adjust the ratio of the prior knowledge during the training phase according to the feature gap, thus guiding the student in an appropriate difficulty. To evaluate the proposed method, we conduct extensive experiments on two image classification benchmarks (i.e. CIFAR100 and ImageNet) and an object detection benchmark (\i.e. MS COCO). The results demonstrate the superiority of our method in performance under varying settings. Besides, our DPK makes the performance of the student model positively correlated with that of the teacher model, which means that we can further boost the accuracy of students by applying larger teachers. More importantly, DPK provides a fast solution in teacher model selection for any given model. Our codes will be publicly available for reproducibility.
Continual Test-time Adaptation (CTA) is a promising art to secure accuracy gains in continually-changing environments. The state-of-the-art adaptations improve out-of-distribution model accuracy via computation-efficient online test-time gradient descents but meanwhile cost about times of memory versus the inference, even if only a small portion of parameters are updated. Such high memory consumption of CTA substantially impedes wide applications of advanced CTA on memory-constrained devices. In this paper, we provide a novel solution, dubbed MECTA, to drastically improve the memory efficiency of gradient-based CTA. Our profiling shows that the major memory overhead comes from the intermediate cache for back-propagation, which scales by the batch size, channel, and layer number. Therefore, we propose to reduce batch sizes, adopt an adaptive normalization layer to maintain stable and accurate predictions, and stop the back-propagation caching heuristically. On the other hand, we prune the networks to reduce the computation and memory overheads in optimization and recover the parameters afterward to avoid forgetting. The proposed MECTA is efficient and can be seamlessly plugged into state-of-the-art CTA algorithms at negligible overhead on computation and memory. On three datasets, CIFAR10, CIFAR100, and ImageNet, MECTA improves the accuracy by at least 6% with constrained memory and significantly reduces the memory costs of ResNet50 on ImageNet by at least 70% with comparable accuracy. Our codes can be accessed at https://github.com/SonyAI/MECTA.
Self-training (ST), or pseudo-labeling has sparked significant interest in the automatic speech recognition (ASR) community recently because of its success in harnessing unlabeled data. Unlike prior semi-supervised learning approaches that relied on iteratively regenerating pseudo-labels (PLs) from a trained model and using them to train a new model, recent state-of-the-art methods perform `continuous training' where PLs are generated using a very recent version of the model being trained. Nevertheless, these approaches still rely on bootstrapping the ST using an initial supervised learning phase where the model is trained on labeled data alone. We believe this has the potential for over-fitting to the labeled dataset in low resource settings and that ST from the start of training should reduce over-fitting. In this paper we show how we can do this by dynamically controlling the evolution of PLs during the training process in ASR. To the best of our knowledge, this is the first study that shows the feasibility of generating PLs from the very start of the training. We are able to achieve this using two techniques that avoid instabilities which lead to degenerate models that do not generalize. Firstly, we control the evolution of PLs through a curriculum that uses the online changes in PLs to control the membership of the cache of PLs and improve generalization. Secondly, we find that by sampling transcriptions from the predictive distribution, rather than only using the best transcription, we can stabilize training further. With these techniques, our ST models match prior works without an external language model.
Knowledge Distillation (KD) is a typical method for training a lightweight student model with the help of a well-trained teacher model. However, most KD methods require access to either the teacher's training data or model parameter, which is unrealistic. To tackle this problem, recent works study KD under data-free and black-box settings. Nevertheless, these works require a large number of queries to the teacher model, which incurs significant monetary and computational costs. To address these problems, we propose a novel method called \emph{query-effIcient Data-free lEarning from blAck-box modeLs} (IDEAL), which aims to query-efficiently learn from black-box model APIs to train a good student without any real data. In detail, IDEAL trains the student model in two stages: data generation and model distillation. Note that IDEAL does not require any query in the data generation stage and queries the teacher only once for each sample in the distillation stage. Extensive experiments on various real-world datasets show the effectiveness of the proposed IDEAL. For instance, IDEAL can improve the performance of the best baseline method DFME by 5.83\% on CIFAR10 dataset with only $0.02\times$ the query budget of DFME.
This work introduces DiGress, a discrete denoising diffusion model for generating graphs with categorical node and edge attributes.Our model utilizes a discrete diffusion process that progressively edits graphs with noise, through the process of adding or removing edges and changing the categories.A graph transformer network is trained to revert this process, simplifying the problem of distribution learning over graphs into a sequence of node and edge classification tasks.We further improve sample quality by introducing a Markovian noise model that preserves the marginal distribution of node and edge types during diffusion, and by incorporating auxiliary graph-theoretic features.A procedure for conditioning the generation on graph-level features is also proposed.DiGress achieves state-of-the-art performance on molecular and non-molecular datasets, with up to 3x validity improvement on a planar graph dataset. It is also the first model to scale to the large GuacaMol dataset containing 1.3M drug-like molecules without the use of molecule-specific representations.
In real-world applications, deep learning models often run in non-stationary environments where the target data distribution continually shifts over time. There have been numerous domain adaptation (DA) methods in both online and offline modes to improve cross-domain adaptation ability. However, these DA methods typically only provide good performance after a long period of adaptation, and perform poorly on new domains before and during adaptation – in what we call the “Unfamiliar Period”, especially when domain shifts happen suddenly and significantly. On the other hand, domain generalization (DG) methods have been proposed to improve the model generalization ability on unadapted domains. However, existing DG works are ineffective for continually changing domains due to severe catastrophic forgetting of learned knowledge. To overcome these limitations of DA and DG in handling the Unfamiliar Period during continual domain shift, we propose RaTP, a framework that focuses on improving models’ target domain generalization (TDG) capability, while also achieving effective target domain adaptation (TDA) capability right after training on certain domains and forgetting alleviation (FA) capability on past domains. RaTP includes a training-free data augmentation module to prepare data for TDG, a novel pseudo-labeling mechanism to provide reliable supervision for TDA, and a prototype contrastive alignment algorithm to align different domains for achieving TDG, TDA and FA. Extensive experiments on Digits, PACS, and DomainNet demonstrate that RaTP significantly outperforms state-of-the-art works from Continual DA, Source-Free DA, Test-Time/Online DA, Single DG, Multiple DG and Unified DA&DG in TDG, and achieves comparable TDA and FA capabilities.
Many real-world continuous control problems are in the dilemma of weighing the pros and cons, multi-objective reinforcement learning (MORL) serves as a generic framework of learning control policies for different preferences over objectives. However, the existing MORL methods either rely on multiple passes of explicit search for finding the Pareto front and therefore are not sample-efficient, or utilizes a shared policy network for coarse knowledge sharing among policies. To boost the sample efficiency of MORL, we propose $Q$-Pensieve, a policy improvement scheme that stores a collection of $Q$-snapshots to jointly determine the policy update direction and thereby enables data sharing at the policy level. We show that $Q$-Pensieve can be naturally integrated with soft policy iteration with convergence guarantee. To substantiate this concept, we propose the technique of $Q$ replay buffer, which stores the learned $Q$-networks from the past iterations, and arrive at a practical actor-critic implementation. Through extensive experiments and an ablation study, we demonstrate that with much fewer samples, the proposed algorithm can outperform the benchmark MORL methods on a variety of MORL benchmark tasks.
Understanding the interaction between multiple agents is crucial for realistic vehicle trajectory prediction. Existing methods have attempted to infer the interaction from the observed past trajectories of agents using pooling, attention, or graph-based methods, which rely on a deterministic approach. However, these methods can fail under complex road structures, as they cannot predict various interactions that may occur in the future. In this paper, we propose a novel approach that uses lane information to predict a stochastic future relationship among agents. To obtain a coarse future motion of agents, our method first predicts the probability of lane-level waypoint occupancy of vehicles. We then utilize the temporal probability of passing adjacent lanes for each agent pair, assuming that agents passing adjacent lanes will highly interact. We also model the interaction using a probabilistic distribution, which allows for multiple possible future interactions. The distribution is learned from the posterior distribution of interaction obtained from ground truth future trajectories. We validate our method on popular trajectory prediction datasets: nuScenes and Argoverse. The results show that the proposed method brings remarkable performance gain in prediction accuracy, and achieves state-of-the-art performance in long-term prediction benchmark dataset.
It’s a meaningful and attractive topic to build a general and inclusive segmentation model that can recognize more categories in various scenarios. A straightforward way is to combine the existing fragmented segmentation datasets and train a multi-dataset network. However, there are two major issues with multi-dataset segmentation: (i) the inconsistent taxonomy demands manual reconciliation to construct a unified taxonomy; (ii) the inflexible one-hot common taxonomy causes time-consuming model retraining and defective supervision of unlabeled categories. In this paper, we investigate the multi-dataset segmentation and propose a scalable Language-guided Multi-dataset Segmentation framework, dubbed LMSeg, which supports both semantic and panoptic segmentation. Specifically, we introduce a pretrained text encoder to map the category names to a text embedding space as a unified taxonomy, instead of using inflexible one-hot label. The model dynamically aligns the segment queries with the category embeddings. Instead of relabeling each dataset with the unified taxonomy, a category-guided decoding module is designed to dynamically guide predictions to each dataset’s taxonomy. Furthermore, we adopt a dataset-aware augmentation strategy that assigns each dataset a specific image augmentation pipeline, which can suit the proper-ties of images from different datasets. Extensive experiments demonstrate that our method achieves significant improvements on four segmentation datasets and three panoptic datasets, while the ablation study evaluates the effectiveness of each component.
Semi-supervised learning aims to train a model using limited labels. State-of-the-art semi-supervised methods for image classification such as PAWS rely on self-supervised representations learned with large-scale unlabeled but curated data. However, PAWS is often less effective when using real-world unlabeled data that is uncurated, e.g., contains out-of-class data. We propose RoPAWS, a robust extension of PAWS that can work with real-world unlabeled data. We first reinterpret PAWS as a generative classifier that models densities using kernel density estimation. From this probabilistic perspective, we calibrate its prediction based on the densities of labeled and unlabeled data, which leads to a simple closed-form solution from the Bayes' rule. We demonstrate that RoPAWS significantly improves PAWS for uncurated Semi-iNat by +5.3% and curated ImageNet by +0.4%.
Beyond the success story of adversarial training (AT) in the recent text domain on top of pre-trained language models (PLMs), our empirical study showcases the inconsistent gains from AT on some tasks, e.g. commonsense reasoning, named entity recognition. This paper investigates AT from the perspective of the contextualized language representation outputted by PLM encoders. We find the current AT attacks lean to generate sub-optimal adversarial examples that can fool the decoder part but have a minor effect on the encoder. However, we find it necessary to effectively deviate the latter one to allow AT to gain. Based on the observation, we propose simple yet effective \textit{Contextualized representation-Adversarial Training} (CreAT), in which the attack is explicitly optimized to deviate the contextualized representation of the encoder. It allows a global optimization of adversarial examples that can fool the entire model. We also find CreAT gives rise to a better direction to optimize the adversarial examples, to let them less sensitive to hyperparameters. Compared to AT, CreAT produces consistent performance gains on a wider range of tasks and is proven to be more effective for language pre-training where only the encoder part is kept for downstream tasks. We achieve the new state-of-the-art performances on a series of challenging benchmarks, e.g. AdvGLUE (59.1 $ \rightarrow $ 61.1), HellaSWAG (93.0 $ \rightarrow $ 94.9), ANLI (68.1 $ \rightarrow $ 69.3).
To afford flexible behaviour, the brain must build internal representations that mirror the structure of variables in the external world. For example, 2D space obeys rules: the same set of actions combine in the same way everywhere (step north, then south, and you won't have moved, wherever you start). We suggest the brain must represent this consistent meaning of actions across space, as it allows you to find new short-cuts and navigate in unfamiliar settings. We term this representation an `actionable representation'. We formulate actionable representations using group and representation theory, and show that, when combined with biological and functional constraints - non-negative firing, bounded neural activity, and precise coding - multiple modules of hexagonal grid cells are the optimal representation of 2D space. We support this claim with intuition, analytic justification, and simulations. Our analytic results normatively explain a set of surprising grid cell phenomena, and make testable predictions for future experiments. Lastly, we highlight the generality of our approach beyond just understanding 2D space. Our work characterises a new principle for understanding and designing flexible internal representations: they should be actionable, allowing animals and machines to predict the consequences of their actions, rather than just encode.
The asymptotic mean squared test error and sensitivity of the Random Features Regression model (RFR) have been recently studied. We build on this work and identify in closed-form the family of Activation Functions (AFs) that minimize a combination of the test error and sensitivity of the RFR under different notions of functional parsimony. We find scenarios under which the optimal AFs are linear, saturated linear functions, or expressible in terms of Hermite polynomials. Finally, we show how using optimal AFs impacts well established properties of the RFR model, such as its double descent curve, and the dependency of its optimal regularization parameter on the observation noise level.