Dynamic environments require adaptive applications. One particular machine learning problem in dynamic environments is open world recognition. It characterizes a continuously changing domain where only some classes are seen in one batch of the training data and such batches can only be learned incrementally. Open world recognition is a demanding task that is, to the best of our knowledge, addressed by only a few methods. This work introduces a modification of the widely known Extreme Value Machine (EVM) to enable open world recognition. Our proposed method extends the EVM with a partial model fitting function by neglecting unaffected space during an update. This reduces the training time by a factor of 28. In addition, we provide a modified model reduction using weighted maximum K-set cover to strictly bound the model complexity and reduce the computational effort by a factor of 3.5 from 2.1 s to 0.6 s. In our experiments, we rigorously evaluate openness with two novel evaluation protocols. The proposed method achieves superior accuracy of about 12 % and computational efficiency in the tasks of image classification and face recognition.
With the tremendous expansion of graphs data, node classification shows its great importance in many real-world applications. Existing graph neural network based methods mainly focus on classifying unlabeled nodes within fixed classes with abundant labeling. However, in many practical scenarios, graph evolves with emergence of new nodes and edges. Novel classes appear incrementally along with few labeling due to its newly emergence or lack of exploration. In this paper, we focus on this challenging but practical graph few-shot class-incremental learning (GFSCIL) problem and propose a novel method called Geometer. Instead of replacing and retraining the fully connected neural network classifer, Geometer predicts the label of a node by finding the nearest class prototype. Prototype is a vector representing a class in the metric space. With the pop-up of novel classes, Geometer learns and adjusts the attention-based prototypes by observing the geometric proximity, uniformity and separability. Teacher-student knowledge distillation and biased sampling are further introduced to mitigate catastrophic forgetting and unbalanced labeling problem respectively. Experimental results on four public datasets demonstrate that Geometer achieves a substantial improvement of 9.46% to 27.60% over state-of-the-art methods.
Time-dependent data-generating distributions have proven to be difficult for gradient-based training of neural networks, as the greedy updates result in catastrophic forgetting of previously learned knowledge. Despite the progress in the field of continual learning to overcome this forgetting, we show that a set of common state-of-the-art methods still suffers from substantial forgetting upon starting to learn new tasks, except that this forgetting is temporary and followed by a phase of performance recovery. We refer to this intriguing but potentially problematic phenomenon as the stability gap. The stability gap had likely remained under the radar due to standard practice in the field of evaluating continual learning models only after each task. Instead, we establish a framework for continual evaluation that uses per-iteration evaluation and we define a new set of metrics to quantify worst-case performance. Empirically we show that experience replay, constraint-based replay, knowledge-distillation, and parameter regularization methods are all prone to the stability gap; and that the stability gap can be observed in class-, task-, and domain-incremental learning benchmarks. Additionally, a controlled experiment shows that the stability gap increases when tasks are more dissimilar. Finally, by disentangling gradients into plasticity and stability components, we propose a conceptual explanation for the stability gap.
Real-world applications require the classification model to adapt to new classes without forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. Typical CIL methods tend to save representative exemplars from former classes to resist forgetting, while recent works find that storing models from history can substantially boost the performance. However, the stored models are not counted into the memory budget, which implicitly results in unfair comparisons. We find that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work, especially for the case with limited memory budgets. As a result, we need to holistically evaluate different CIL methods at different memory scales and simultaneously consider accuracy and memory size for measurement. On the other hand, we dive deeply into the construction of the memory buffer for memory efficiency. By analyzing the effect of different layers in the network, we find that shallow and deep layers have different characteristics in CIL. Motivated by this, we propose a simple yet effective baseline, denoted as MEMO for Memory-efficient Expandable MOdel. MEMO extends specialized layers based on the shared generalized representations, efficiently extracting diverse representations with modest cost and maintaining representative exemplars. Extensive experiments on benchmark datasets validate MEMO's competitive performance. Code is available at: https://github.com/wangkiw/ICLR23-MEMO
When deploying a robot to a new task, one often has to train it to detect novel objects, which is time-consuming and labor-intensive. We present TAILOR -- a method and system for object registration with active and incremental learning. When instructed by a human teacher to register an object, TAILOR is able to automatically select viewpoints to capture informative images by actively exploring viewpoints, and employs a fast incremental learning algorithm to learn new objects without potential forgetting of previously learned objects. We demonstrate the effectiveness of our method with a KUKA robot to learn novel objects used in a real-world gearbox assembly task through natural interactions.
Exemplar-free incremental learning is extremely challenging due to inaccessibility of data from old tasks. In this paper, we attempt to exploit the knowledge encoded in a previously trained classification model to handle the catastrophic forgetting problem in continual learning. Specifically, we introduce a so-called knowledge delegator, which is capable of transferring knowledge from the trained model to a randomly re-initialized new model by generating informative samples. Given the previous model only, the delegator is effectively learned using a self-distillation mechanism in a data-free manner. The knowledge extracted by the delegator is then utilized to maintain the performance of the model on old tasks in incremental learning. This simple incremental learning framework surpasses existing exemplar-free methods by a large margin on four widely used class incremental benchmarks, namely CIFAR-100, ImageNet-Subset, Caltech-101 and Flowers-102. Notably, we achieve comparable performance to some exemplar-based methods without accessing any exemplars.
It is common to have continuous streams of new data that need to be introduced in the system in real-world applications. The model needs to learn newly added capabilities (future tasks) while retaining the old knowledge (past tasks). Incremental learning has recently become increasingly appealing for this problem. Task-incremental learning is a kind of incremental learning where task identity of newly included task (a set of classes) remains known during inference. A common goal of task-incremental methods is to design a network that can operate on minimal size, maintaining decent performance. To manage the stability-plasticity dilemma, different methods utilize replay memory of past tasks, specialized hardware, regularization monitoring etc. However, these methods are still less memory efficient in terms of architecture growth or input data costs. In this study, we present a simple yet effective adjustment network (SAN) for task incremental learning that achieves near state-of-the-art performance while using minimal architectural size without using memory instances compared to previous state-of-the-art approaches. We investigate this approach on both 3D point cloud object (ModelNet40) and 2D image (CIFAR10, CIFAR100, MiniImageNet, MNIST, PermutedMNIST, notMNIST, SVHN, and FashionMNIST) recognition tasks and establish a strong baseline result for a fair comparison with existing methods. On both 2D and 3D domains, we also observe that SAN is primarily unaffected by different task orders in a task-incremental setting.
As progress is made on training machine learning models on incrementally expanding classification tasks (i.e., incremental learning), a next step is to translate this progress to industry expectations. One technique missing from incremental learning is automatic architecture design via Neural Architecture Search (NAS). In this paper, we show that leveraging NAS for incremental learning results in strong performance gains for classification tasks. Specifically, we contribute the following: first, we create a strong baseline approach for incremental learning based on Differentiable Architecture Search (DARTS) and state-of-the-art incremental learning strategies, outperforming many existing strategies trained with similar-sized popular architectures; second, we extend the idea of architecture search to regularize architecture forgetting, boosting performance past our proposed baseline. We evaluate our method on both RF signal and image classification tasks, and demonstrate we can achieve up to a 10% performance increase over state-of-the-art methods. Most importantly, our contribution enables learning from continuous distributions on real-world application data for which the complexity of the data distribution is unknown, or the modality less explored (such as RF signal classification).
Continual learning requires the model to maintain the learned knowledge while learning from a non-i.i.d data stream continually. Due to the single-pass training setting, online continual learning is very challenging, but it is closer to the real-world scenarios where quick adaptation to new data is appealing. In this paper, we focus on online class-incremental learning setting in which new classes emerge over time. Almost all existing methods are replay-based with a softmax classifier. However, the inherent logits bias problem in the softmax classifier is a main cause of catastrophic forgetting while existing solutions are not applicable for online settings. To bypass this problem, we abandon the softmax classifier and propose a novel generative framework based on the feature space. In our framework, a generative classifier which utilizes replay memory is used for inference, and the training objective is a pair-based metric learning loss which is proven theoretically to optimize the feature space in a generative way. In order to improve the ability to learn new data, we further propose a hybrid of generative and discriminative loss to train the model. Extensive experiments on several benchmarks, including newly introduced task-free datasets, show that our method beats a series of state-of-the-art replay-based methods with discriminative classifiers, and reduces catastrophic forgetting consistently with a remarkable margin.
Tabular data (or tables) are the most widely used data format in machine learning (ML). However, ML models often assume the table structure keeps fixed in training and testing. Before ML modeling, heavy data cleaning is required to merge disparate tables with different columns. This preprocessing often incurs significant data waste (e.g., removing unmatched columns and samples). How to learn ML models from multiple tables with partially overlapping columns? How to incrementally update ML models as more columns become available over time? Can we leverage model pretraining on multiple distinct tables? How to train an ML model which can predict on an unseen table? To answer all those questions, we propose to relax fixed table structures by introducing a Transferable Tabular Transformer (TransTab) for tables. The goal of TransTab is to convert each sample (a row in the table) to a generalizable embedding vector, and then apply stacked transformers for feature encoding. One methodology insight is combining column description and table cells as the raw input to a gated transformer model. The other insight is to introduce supervised and self-supervised pretraining to improve model performance. We compare TransTab with multiple baseline methods on diverse benchmark datasets and five oncology clinical trial datasets. Overall, TransTab ranks 1.00, 1.00, 1.78 out of 12 methods in supervised learning, feature incremental learning, and transfer learning scenarios, respectively; and the proposed pretraining leads to 2.3% AUC lift on average over the supervised learning.
Machine learning has become omnipresent with applications in various safety-critical domains such as medical, law, and transportation. In these domains, high-stake decisions provided by machine learning necessitate researchers to design interpretable models, where the prediction is understandable to a human. In interpretable machine learning, rule-based classifiers are particularly effective in representing the decision boundary through a set of rules comprising input features. The interpretability of rule-based classifiers is in general related to the size of the rules, where smaller rules are considered more interpretable. To learn such a classifier, the brute-force direct approach is to consider an optimization problem that tries to learn the smallest classification rule that has close to maximum accuracy. This optimization problem is computationally intractable due to its combinatorial nature and thus, the problem is not scalable in large datasets. To this end, in this paper we study the triangular relationship among the accuracy, interpretability, and scalability of learning rule-based classifiers. The contribution of this paper is an interpretable learning framework IMLI, that is based on maximum satisfiability (MaxSAT) for synthesizing classification rules expressible in proposition logic. Despite the progress of MaxSAT solving in the last decade, the straightforward MaxSAT-based solution cannot scale. Therefore, we incorporate an efficient incremental learning technique inside the MaxSAT formulation by integrating mini-batch learning and iterative rule-learning. In our experiments, IMLI achieves the best balance among prediction accuracy, interpretability, and scalability. As an application, we deploy IMLI in learning popular interpretable classifiers such as decision lists and decision sets.
There have been emerging a number of benchmarks and techniques for the detection of deepfakes. However, very few works study the detection of incrementally appearing deepfakes in the real-world scenarios. To simulate the wild scenes, this paper suggests a continual deepfake detection benchmark (CDDB) over a new collection of deepfakes from both known and unknown generative models. The suggested CDDB designs multiple evaluations on the detection over easy, hard, and long sequence of deepfake tasks, with a set of appropriate measures. In addition, we exploit multiple approaches to adapt multiclass incremental learning methods, commonly used in the continual visual recognition, to the continual deepfake detection problem. We evaluate existing methods, including their adapted ones, on the proposed CDDB. Within the proposed benchmark, we explore some commonly known essentials of standard continual learning. Our study provides new insights on these essentials in the context of continual deepfake detection. The suggested CDDB is clearly more challenging than the existing benchmarks, which thus offers a suitable evaluation avenue to the future research. Both data and code are available at https://github.com/Coral79/CDDB.
The knowledge of a well-trained deep neural network (a.k.a. the "teacher") is valuable for learning similar tasks. Knowledge distillation extracts knowledge from the teacher and integrates it with the target model (a.k.a. the "student"), which expands the student's knowledge and improves its learning efficacy. Instead of enforcing the teacher to work on the same task as the student, we borrow the knowledge from a teacher trained from a general label space -- in this "Generalized Knowledge Distillation (GKD)", the classes of the teacher and the student may be the same, completely different, or partially overlapped. We claim that the comparison ability between instances acts as an essential factor threading knowledge across tasks, and propose the RElationship FacIlitated Local cLassifiEr Distillation (REFILLED) approach, which decouples the GKD flow of the embedding and the top-layer classifier. In particular, different from reconciling the instance-label confidence between models, REFILLED requires the teacher to reweight the hard tuples pushed forward by the student and then matches the similarity comparison levels between instances. An embedding-induced classifier based on the teacher model supervises the student's classification confidence and adaptively emphasizes the most related supervision from the teacher. REFILLED demonstrates strong discriminative ability when the classes of the teacher vary from the same to a fully non-overlapped set w.r.t. the student. It also achieves state-of-the-art performance on standard knowledge distillation, one-step incremental learning, and few-shot learning tasks.
Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly in intelligent diagnosis systems where initially only training data of a limited number of diseases are available. In this case, updating the intelligent system with data of new diseases would inevitably downgrade its performance on previously learned diseases. Inspired by the process of learning new knowledge in human brains, we propose a Bayesian generative model for continual learning built on a fixed pre-trained feature extractor. In this model, knowledge of each old class can be compactly represented by a collection of statistical distributions, e.g. with Gaussian mixture models, and naturally kept from forgetting in continual learning over time. Unlike existing class-incremental learning methods, the proposed approach is not sensitive to the continual learning process and can be additionally well applied to the data-incremental learning scenario. Experiments on multiple medical and natural image classification tasks showed that the proposed approach outperforms state-of-the-art approaches which even keep some images of old classes during continual learning of new classes.
Many deep learning applications, like keyword spotting, require the incorporation of new concepts (classes) over time, referred to as Class Incremental Learning (CIL). The major challenge in CIL is catastrophic forgetting, i.e., preserving as much of the old knowledge as possible while learning new tasks. Various techniques, such as regularization, knowledge distillation, and the use of exemplars, have been proposed to resolve this issue. However, prior works primarily focus on the incremental learning step, while ignoring the optimization during the base model training. We hypothesize that a more transferable and generalizable feature representation from the base model would be beneficial to incremental learning. In this work, we adopt multitask learning during base model training to improve the feature generalizability. Specifically, instead of training a single model with all the base classes, we decompose the base classes into multiple subsets and regard each of them as a task. These tasks are trained concurrently and a shared feature extractor is obtained for incremental learning. We evaluate our approach on two datasets under various configurations. The results show that our approach enhances the average incremental learning accuracy by up to 5.5%, which enables more reliable and accurate keyword spotting over time. Moreover, the proposed approach can be combined with many existing techniques and provides additional performance gain.
In this paper is described the ANFIS Unit Neural Network, a deep neural network where each neuron is an independent ANFIS. Two use cases of this network are shown to test the capability of the network. (i) Classification of five imagined words. (ii) Incremental learning in the task of detecting Imagined Word Segments vs. Idle State Segments. In both cases, the proposed network outperforms the conventional methods. Additionally, is described a process of classification where instead of taking the whole instance as one example, each instance is decomposed into a set of smaller instances, and the classification is done by a majority vote over all the predictions of the set. The codes to build the AU-NN used in this paper, are available on the github repository https://github.com/tonahdztoro/AU_NN.
Given entities and their interactions in the web data, which may have occurred at different time, how can we find communities of entities and track their evolution? In this paper, we approach this important task from graph clustering perspective. Recently, state-of-the-art clustering performance in various domains has been achieved by deep clustering methods. Especially, deep graph clustering (DGC) methods have successfully extended deep clustering to graph-structured data by learning node representations and cluster assignments in a joint optimization framework. Despite some differences in modeling choices (e.g., encoder architectures), existing DGC methods are mainly based on autoencoders and use the same clustering objective with relatively minor adaptations. Also, while many real-world graphs are dynamic, previous DGC methods considered only static graphs. In this work, we develop CGC, a novel end-to-end framework for graph clustering, which fundamentally differs from existing methods. CGC learns node embeddings and cluster assignments in a contrastive graph learning framework, where positive and negative samples are carefully selected in a multi-level scheme such that they reflect hierarchical community structures and network homophily. Also, we extend CGC for time-evolving data, where temporal graph clustering is performed in an incremental learning fashion, with the ability to detect change points. Extensive evaluation on real-world graphs demonstrates that the proposed CGC consistently outperforms existing methods.
Deep neural network (DNN) suffers from catastrophic forgetting when learning incrementally, which greatly limits its applications. Although maintaining a handful of samples (called `exemplars`) of each task could alleviate forgetting to some extent, existing methods are still limited by the small number of exemplars since these exemplars are too few to carry enough task-specific knowledge, and therefore the forgetting remains. To overcome this problem, we propose to `imagine` diverse counterparts of given exemplars referring to the abundant semantic-irrelevant information from unlabeled data. Specifically, we develop a learnable feature generator to diversify exemplars by adaptively generating diverse counterparts of exemplars based on semantic information from exemplars and semantically-irrelevant information from unlabeled data. We introduce semantic contrastive learning to enforce the generated samples to be semantic consistent with exemplars and perform semanticdecoupling contrastive learning to encourage diversity of generated samples. The diverse generated samples could effectively prevent DNN from forgetting when learning new tasks. Our method does not bring any extra inference cost and outperforms state-of-the-art methods on two benchmarks CIFAR-100 and ImageNet-Subset by a clear margin.
Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as different weather conditions, they are prone to forgetting previously learned information. This catastrophic forgetting is typically addressed via incremental learning approaches which usually re-train the model by either keeping a memory bank of training samples or keeping a copy of the entire model or model parameters for each scenario. While these approaches show impressive results, they can be prone to scalability issues and their applicability for autonomous driving in all weather conditions has not been shown. In this paper we propose DISC -- Domain Incremental through Statistical Correction -- a simple online zero-forgetting approach which can incrementally learn new tasks (i.e weather conditions) without requiring re-training or expensive memory banks. The only information we store for each task are the statistical parameters as we categorize each domain by the change in first and second order statistics. Thus, as each task arrives, we simply 'plug and play' the statistical vectors for the corresponding task into the model and it immediately starts to perform well on that task. We show the efficacy of our approach by testing it for object detection in a challenging domain-incremental autonomous driving scenario where we encounter different adverse weather conditions, such as heavy rain, fog, and snow.
Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already learned while updating their parameters in absence of the original training data. Previous works extended standard classification methods in the object detection task, mainly adopting the knowledge distillation framework. However, we argue that object detection introduces an additional problem, which has been overlooked. While objects belonging to new classes are learned thanks to their annotations, if no supervision is provided for other objects that may still be present in the input, the model learns to associate them to background regions. We propose to handle these missing annotations by revisiting the standard knowledge distillation framework. Our approach outperforms current state-of-the-art methods in every setting of the Pascal-VOC dataset. We further propose an extension to instance segmentation, outperforming the other baselines. Code can be found here: https://github.com/fcdl94/MMA