A desirable objective in self-supervised learning (SSL) is to avoid feature collapse. Whitening loss guarantees collapse avoidance by minimizing the distance between embeddings of positive pairs under the conditioning that the embeddings from different views are whitened. In this paper, we propose a framework with an informative indicator to analyze whitening loss, which provides a clue to demystify several interesting phenomena as well as a pivoting point connecting to other SSL methods. We reveal that batch whitening (BW) based methods do not impose whitening constraints on the embedding, but they only require the embedding to be full-rank. This full-rank constraint is also sufficient to avoid dimensional collapse. Based on our analysis, we propose channel whitening with random group partition (CW-RGP), which exploits the advantages of BW-based methods in preventing collapse and avoids their disadvantages requiring large batch size. Experimental results on ImageNet classification and COCO object detection reveal that the proposed CW-RGP possesses a promising potential for learning good representations.

Deep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour have been long standing issues in DQNs. The unstable behaviour is often characterised by overestimation in the $Q$-values, commonly referred to as the overestimation bias. To address the overestimation bias and the divergent behaviour, a number of heuristic extensions have been proposed. Notably, multi-step updates have been shown to drastically reduce unstable behaviour while improving agent's training performance. However, agents are often highly sensitive to the selection of the multi-step update horizon ($n$), and our empirical experiments show that a poorly chosen static value for $n$ can in many cases lead to worse performance than single-step DQN. Inspired by the success of $n$-step DQN and the effects that multi-step updates have on overestimation bias, this paper proposes a new algorithm that we call `Elastic Step DQN' (ES-DQN). It dynamically varies the step size horizon in multi-step updates based on the similarity of states visited. Our empirical evaluation shows that ES-DQN out-performs $n$-step with fixed $n$ updates, Double DQN and Average DQN in several OpenAI Gym environments while at the same time alleviating the overestimation bias.

Communication within or between complex systems is commonplace in the natural sciences and fields such as graph neural networks. The brain is a perfect example of such a complex system, where communication between brain regions is constantly being orchestrated. To analyze communication, the brain is often split up into anatomical regions that each perform certain computations. These regions must interact and communicate with each other to perform tasks and support higher-level cognition. On a macroscale, these regions communicate through signal propagation along the cortex and along white matter tracts over longer distances. When and what types of signals are communicated over time is an unsolved problem and is often studied using either functional or structural data. In this paper, we propose a non-linear generative approach to communication from functional data. We address three issues with common connectivity approaches by explicitly modeling the directionality of communication, finding communication at each timestep, and encouraging sparsity. To evaluate our model, we simulate temporal data that has sparse communication between nodes embedded in it and show that our model can uncover the expected communication dynamics. Subsequently, we apply our model to temporal neural data from multiple tasks and show that our approach models communication that is more specific to each task. The specificity of our method means it can have an impact on the understanding of psychiatric disorders, which are believed to be related to highly specific communication between brain regions compared to controls. In sum, we propose a general model for dynamic communication learning on graphs, and show its applicability to a subfield of the natural sciences, with potential widespread scientific impact.

Given a labeled training set and a collection of unlabeled data, the goal of active learning (AL) is to identify the best unlabeled points to label. In this comprehensive study, we analyze the performance of a variety of AL algorithms on deep neural networks trained on 69 real-world tabular classification datasets from the OpenML-CC18 benchmark. We consider different data regimes and the effect of self-supervised model pre-training. Surprisingly, we find that the classical margin sampling technique matches or outperforms all others, including current state-ofart, in a wide range of experimental settings. To researchers, we hope to encourage rigorous benchmarking against margin, and to practitioners facing tabular data labeling constraints that hyper-parameter-free margin may often be all they need. Active learning (AL), the problem of identifying examples to label, is an important problem in machine learning since obtaining labels for data is oftentimes a costly manual process.

Safe path planning is critical for bipedal robots to operate in safety-critical environments. Common path planning algorithms, such as RRT or RRT*, typically use geometric or kinematic collision check algorithms to ensure collision-free paths toward the target position. However, such approaches may generate non-smooth paths that do not comply with the dynamics constraints of walking robots. It has been shown that the control barrier function (CBF) can be integrated with RRT/RRT* to synthesize dynamically feasible collision-free paths. Yet, existing work has been limited to simple circular or elliptical shape obstacles due to the challenging nature of constructing appropriate barrier functions to represent irregular-shaped obstacles. In this paper, we present a CBF-based RRT* algorithm for bipedal robots to generate a collision-free path through complex space with polynomial-shaped obstacles. In particular, we used logistic regression to construct polynomial barrier functions from a grid map of the environment to represent arbitrarily shaped obstacles. Moreover, we developed a multi-step CBF steering controller to ensure the efficiency of free space exploration. The proposed approach was first validated in simulation for a differential drive model, and then experimentally evaluated with a 3D humanoid robot, Digit, in a lab setting with randomly placed obstacles.

Medical conversations between patients and medical professionals have implicit functional sections, such as "history taking", "summarization", "education", and "care plan." In this work, we are interested in learning to automatically extract these sections. A direct approach would require collecting large amounts of expert annotations for this task, which is inherently costly due to the contextual inter-and-intra variability between these sections. This paper presents an approach that tackles the problem of learning to classify medical dialogue into functional sections without requiring a large number of annotations. Our approach combines pseudo-labeling and human-in-the-loop. First, we bootstrap using weak supervision with pseudo-labeling to generate dialogue turn-level pseudo-labels and train a transformer-based model, which is then applied to individual sentences to create noisy sentence-level labels. Second, we iteratively refine sentence-level labels using a cluster-based human-in-the-loop approach. Each iteration requires only a few dozen annotator decisions. We evaluate the results on an expert-annotated dataset of 100 dialogues and find that while our models start with 69.5% accuracy, we can iteratively improve it to 82.5%. The code used to perform all experiments described in this paper can be found here: https://github.com/curai/curai-research/tree/main/functional-sections.

For many applications of probabilistic classifiers it is important that the predicted confidence vectors reflect true probabilities (one says that the classifier is calibrated). It has been shown that common models fail to satisfy this property, making reliable methods for measuring and improving calibration important tools. Unfortunately, obtaining these is far from trivial for problems with many classes. We propose two techniques that can be used in tandem. First, a reduced calibration method transforms the original problem into a simpler one. We prove for several notions of calibration that solving the reduced problem minimizes the corresponding notion of miscalibration in the full problem, allowing the use of non-parametric recalibration methods that fail in higher dimensions. Second, we propose class-wise calibration methods, based on intuition building on a phenomenon called neural collapse and the observation that most of the accurate classifiers found in practice can be thought of as a union of K different functions which can be recalibrated separately, one for each class. These typically out-perform their non class-wise counterparts, especially for classifiers trained on imbalanced data sets. Applying the two methods together results in class-wise reduced calibration algorithms, which are powerful tools for reducing the prediction and per-class calibration errors. We demonstrate our methods on real and synthetic datasets and release all code as open source at https://github.com/appliedAI-Initiative

This paper presents our strategy to address the SemEval-2022 Task 3 PreTENS: Presupposed Taxonomies Evaluating Neural Network Semantics. The goal of the task is to identify if a sentence is deemed acceptable or not, depending on the taxonomic relationship that holds between a noun pair contained in the sentence. For sub-task 1 -- binary classification -- we propose an effective way to enhance the robustness and the generalizability of language models for better classification on this downstream task. We design a two-stage fine-tuning procedure on the ELECTRA language model using data augmentation techniques. Rigorous experiments are carried out using multi-task learning and data-enriched fine-tuning. Experimental results demonstrate that our proposed model, UU-Tax, is indeed able to generalize well for our downstream task. For sub-task 2 -- regression -- we propose a simple classifier that trains on features obtained from Universal Sentence Encoder (USE). In addition to describing the submitted systems, we discuss other experiments that employ pre-trained language models and data augmentation techniques. For both sub-tasks, we perform error analysis to further understand the behaviour of the proposed models. We achieved a global F1_Binary score of 91.25% in sub-task 1 and a rho score of 0.221 in sub-task 2.

When analyzing a dataset, it can be useful to assess how smooth the decision boundaries need to be for a model to better fit the data. This paper addresses this question by proposing the quantification of how much should the 'rigid' decision boundaries, produced by an algorithm that naturally finds such solutions, be relaxed to obtain a performance improvement. The approach we propose starts with the rigid decision boundaries of a seed Decision Tree (seed DT), which is used to initialize a Neural DT (NDT). The initial boundaries are challenged by relaxing them progressively through training the NDT. During this process, we measure the NDT's performance and decision agreement to its seed DT. We show how these two measures can help the user in figuring out how expressive his model should be, before exploring it further via model selection. The validity of our approach is demonstrated with experiments on simulated and benchmark datasets.

We show how to develop sampling-based alternating least squares (ALS) algorithms for decomposition of tensors into any tensor network (TN) format. Provided the TN format satisfies certain mild assumptions, resulting algorithms will have input sublinear per-iteration cost. Unlike most previous works on sampling-based ALS methods for tensor decomposition, the sampling in our framework is done according to the exact leverage score distribution of the design matrices in the ALS subproblems. We implement and test two tensor decomposition algorithms that use our sampling framework in a feature extraction experiment where we compare them against a number of other decomposition algorithms.