Few-shot learning aims to fast adapt a deep model from a few examples. While pre-training and meta-training can create deep models powerful for few-shot generalization, we find that pre-training and meta-training focuses respectively on cross-domain transferability and cross-task transferability, which restricts their data efficiency in the entangled settings of domain shift and task shift. We thus propose the Omni-Training framework to seamlessly bridge pre-training and meta-training for data-efficient few-shot learning. Our first contribution is a tri-flow Omni-Net architecture. Besides the joint representation flow, Omni-Net introduces two parallel flows for pre-training and meta-training, responsible for improving domain transferability and task transferability respectively. Omni-Net further coordinates the parallel flows by routing their representations via the joint-flow, enabling knowledge transfer across flows. Our second contribution is the Omni-Loss, which introduces a self-distillation strategy separately on the pre-training and meta-training objectives for boosting knowledge transfer throughout different training stages. Omni-Training is a general framework to accommodate many existing algorithms. Evaluations justify that our single framework consistently and clearly outperforms the individual state-of-the-art methods on both cross-task and cross-domain settings in a variety of classification, regression and reinforcement learning problems.

For decades, a variety of predictive approaches have been proposed and evaluated in terms of their prediction capability for Alzheimer's Disease (AD) and its precursor - mild cognitive impairment (MCI). Most of them focused on prediction or identification of statistical differences among different clinical groups or phases (e.g., longitudinal studies). The continuous nature of AD development and transition states between successive AD related stages have been overlooked, especially in binary or multi-class classification. Though a few progression models of AD have been studied recently, they were mainly designed to determine and compare the order of specific biomarkers. How to effectively predict the individual patient's status within a wide spectrum of continuous AD progression has been largely overlooked. In this work, we developed a novel learning-based embedding framework to encode the intrinsic relations among AD related clinical stages by a set of meaningful embedding vectors in the latent space (Disease2Vec). We named this process as disease embedding. By disease em-bedding, the framework generates a disease embedding tree (DETree) which effectively represents different clinical stages as a tree trajectory reflecting AD progression and thus can be used to predict clinical status by projecting individuals onto this continuous trajectory. Through this model, DETree can not only perform efficient and accurate prediction for patients at any stages of AD development (across five clinical groups instead of typical two groups), but also provide richer status information by examining the projecting locations within a wide and continuous AD progression process.

Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community. In this work, we construct a structural causal model among identity labels, identity-specific factors (clothes/shoes color etc), and domain-specific factors (background, viewpoints etc). According to the causal analysis, we propose a novel Domain Invariant Representation Learning for generalizable person Re-Identification (DIR-ReID) framework. Specifically, we first propose to disentangle the identity-specific and domain-specific feature spaces, based on which we propose an effective algorithmic implementation for backdoor adjustment, essentially serving as a causal intervention towards the SCM. Extensive experiments have been conducted, showing that DIR-ReID outperforms state-of-the-art methods on large-scale domain generalization ReID benchmarks.

Difference-of-Convex (DC) minimization, referring to the problem of minimizing the difference of two convex functions, has been found rich applications in statistical learning and studied extensively for decades. However, existing methods are primarily based on multi-stage convex relaxation, only leading to weak optimality of critical points. This paper proposes a coordinate descent method for minimizing a class of DC functions based on sequential nonconvex approximation. Our approach iteratively solves a nonconvex one-dimensional subproblem globally, and it is guaranteed to converge to a coordinate-wise stationary point. We prove that this new optimality condition is always stronger than the standard critical point condition and directional point condition under a mild \textit{locally bounded nonconvexity assumption}. For comparisons, we also include a naive variant of coordinate descent methods based on sequential convex approximation in our study. When the objective function satisfies a \textit{globally bounded nonconvexity assumption} and \textit{Luo-Tseng error bound assumption}, coordinate descent methods achieve \textit{Q-linear} convergence rate. Also, for many applications of interest, we show that the nonconvex one-dimensional subproblem can be computed exactly and efficiently using a breakpoint searching method. Finally, we have conducted extensive experiments on several statistical learning tasks to show the superiority of our approach. Keywords: Coordinate Descent, DC Minimization, DC Programming, Difference-of-Convex Programs, Nonconvex Optimization, Sparse Optimization, Binary Optimization.

The coverage of different stakeholders mentioned in the news articles significantly impacts the slant or polarity detection of the concerned news publishers. For instance, the pro-government media outlets would give more coverage to the government stakeholders to increase their accessibility to the news audiences. In contrast, the anti-government news agencies would focus more on the views of the opponent stakeholders to inform the readers about the shortcomings of government policies. In this paper, we address the problem of stakeholder extraction from news articles and thereby determine the inherent bias present in news reporting. Identifying potential stakeholders in multi-topic news scenarios is challenging because each news topic has different stakeholders. The research presented in this paper utilizes both contextual information and external knowledge to identify the topic-specific stakeholders from news articles. We also apply a sequential incremental clustering algorithm to group the entities with similar stakeholder types. We carried out all our experiments on news articles on four Indian government policies published by numerous national and international news agencies. We also further generalize our system, and the experimental results show that the proposed model can be extended to other news topics.

Transformers have become the state-of-the-art neural network architecture across numerous domains of machine learning. This is partly due to their celebrated ability to transfer and to learn in-context based on few examples. Nevertheless, the mechanisms by which Transformers become in-context learners are not well understood and remain mostly an intuition. Here, we argue that training Transformers on auto-regressive tasks can be closely related to well-known gradient-based meta-learning formulations. We start by providing a simple weight construction that shows the equivalence of data transformations induced by 1) a single linear self-attention layer and by 2) gradient-descent (GD) on a regression loss. Motivated by that construction, we show empirically that when training self-attention-only Transformers on simple regression tasks either the models learned by GD and Transformers show great similarity or, remarkably, the weights found by optimization match the construction. Thus we show how trained Transformers implement gradient descent in their forward pass. This allows us, at least in the domain of regression problems, to mechanistically understand the inner workings of optimized Transformers that learn in-context. Furthermore, we identify how Transformers surpass plain gradient descent by an iterative curvature correction and learn linear models on deep data representations to solve non-linear regression tasks. Finally, we discuss intriguing parallels to a mechanism identified to be crucial for in-context learning termed induction-head (Olsson et al., 2022) and show how it could be understood as a specific case of in-context learning by gradient descent learning within Transformers.

Algorithmic solutions for multi-object tracking (MOT) are a key enabler for applications in autonomous navigation and applied ocean sciences. State-of-the-art MOT methods fully rely on a statistical model and typically use preprocessed sensor data as measurements. In particular, measurements are produced by a detector that extracts potential object locations from the raw sensor data collected for a discrete time step. This preparatory processing step reduces data flow and computational complexity but may result in a loss of information. State-of-the-art Bayesian MOT methods that are based on belief propagation (BP) systematically exploit graph structures of the statistical model to reduce computational complexity and improve scalability. However, as a fully model-based approach, BP can only provide suboptimal estimates when there is a mismatch between the statistical model and the true data-generating process. Existing BP-based MOT methods can further only make use of preprocessed measurements. In this paper, we introduce a variant of BP that combines model-based with data-driven MOT. The proposed neural enhanced belief propagation (NEBP) method complements the statistical model of BP by information learned from raw sensor data. This approach conjectures that the learned information can reduce model mismatch and thus improve data association and false alarm rejection. Our NEBP method improves tracking performance compared to model-based methods. At the same time, it inherits the advantages of BP-based MOT, i.e., it scales only quadratically in the number of objects, and it can thus generate and maintain a large number of object tracks. We evaluate the performance of our NEBP approach for MOT on the nuScenes autonomous driving dataset and demonstrate that it has state-of-the-art performance.

Student success models might be prone to develop weak spots, i.e., examples hard to accurately classify due to insufficient representation during model creation. This weakness is one of the main factors undermining users' trust, since model predictions could for instance lead an instructor to not intervene on a student in need. In this paper, we unveil the need of detecting and characterizing unknown unknowns in student success prediction in order to better understand when models may fail. Unknown unknowns include the students for which the model is highly confident in its predictions, but is actually wrong. Therefore, we cannot solely rely on the model's confidence when evaluating the predictions quality. We first introduce a framework for the identification and characterization of unknown unknowns. We then assess its informativeness on log data collected from flipped courses and online courses using quantitative analyses and interviews with instructors. Our results show that unknown unknowns are a critical issue in this domain and that our framework can be applied to support their detection. The source code is available at https://github.com/epfl-ml4ed/unknown-unknowns.

Given a finite and noisy dataset generated with a closed-form mathematical model, when is it possible to learn the true generating model from the data alone? This is the question we investigate here. We show that this model-learning problem displays a transition from a low-noise phase in which the true model can be learned, to a phase in which the observation noise is too high for the true model to be learned by any method. Both in the low-noise phase and in the high-noise phase, probabilistic model selection leads to optimal generalization to unseen data. This is in contrast to standard machine learning approaches, including artificial neural networks, which in this particular problem are limited, in the low-noise phase, by their ability to interpolate. In the transition region between the learnable and unlearnable phases, generalization is hard for all approaches including probabilistic model selection.

We propose a dynamic network sampling scheme to optimize block recovery for stochastic blockmodel (SBM) in the case where it is prohibitively expensive to observe the entire graph. Theoretically, we provide justification of our proposed Chernoff-optimal dynamic sampling scheme via the Chernoff information. Practically, we evaluate the performance, in terms of block recovery, of our method on several real datasets from different domains. Both theoretically and practically results suggest that our method can identify vertices that have the most impact on block structure so that one can only check whether there are edges between them to save significant resources but still recover the block structure.