Navigating Extremes: Dynamic Sparsity in Large Output Space

In recent years, Dynamic Sparse Training (DST) has emerged as an alternative to post-training pruning for generating efficient models. In principle, DST allows for a more memory efficient training process, as it maintains sparsity throughout the entire training run. However, current DST implementations fail to capitalize on this in practice. Because sparse matrix multiplication is much less efficient than dense matrix multiplication on GPUs, most implementations simulate sparsity by masking weights. In this paper, we leverage recent advances in semi-structured sparse training to apply DST in the domain of classification with large output spaces, where memory-efficiency is paramount. With a label space of possibly millions of candidates, the classification layer alone will consume several gigabytes of memory. Switching from a dense to a fixed fan-in sparse layer updated with sparse evolutionary training (SET); however, severely hampers training convergence, especially at the largest label spaces. We find that poor gradient flow from the sparse classifier to the dense text encoder make it difficult to learn good input representations. By employing an intermediate layer or adding an auxiliary training objective, we recover most of the generalisation performance of the dense model. Overall, we demonstrate the applicability and practical benefits of DST in a challenging domain -- characterized by a highly skewed label distribution that differs substantially from typical DST benchmark datasets -- which enables end-to-end training with millions of labels on commodity hardware.

A General Online Algorithm for Optimizing Complex Performance Metrics

We consider sequential maximization of performance metrics that are general functions of a confusion matrix of a classifier (such as precision, F-measure, or G-mean). Such metrics are, in general, non-decomposable over individual instances, making their optimization very challenging. While they have been extensively studied under different frameworks in the batch setting, their analysis in the online learning regime is very limited, with only a few distinguished exceptions. In this paper, we introduce and analyze a general online algorithm that can be used in a straightforward way with a variety of complex performance metrics in binary, multi-class, and multi-label classification problems. The algorithm's update and prediction rules are appealingly simple and computationally efficient without the need to store any past data. We show the algorithm attains $\mathcal{O}(\frac{\ln n}{n})$ regret for concave and smooth metrics and verify the efficiency of the proposed algorithm in empirical studies.

Learning label-label correlations in Extreme Multi-label Classification via Label Features

Extreme Multi-label Text Classification (XMC) involves learning a classifier that can assign an input with a subset of most relevant labels from millions of label choices. Recent works in this domain have increasingly focused on a symmetric problem setting where both input instances and label features are short-text in nature. Short-text XMC with label features has found numerous applications in areas such as query-to-ad-phrase matching in search ads, title-based product recommendation, prediction of related searches. In this paper, we propose Gandalf, a novel approach which makes use of a label co-occurrence graph to leverage label features as additional data points to supplement the training distribution. By exploiting the characteristics of the short-text XMC problem, it leverages the label features to construct valid training instances, and uses the label graph for generating the corresponding soft-label targets, hence effectively capturing the label-label correlations. Surprisingly, models trained on these new training instances, although being less than half of the original dataset, can outperform models trained on the original dataset, particularly on the PSP@k metric for tail labels. With this insight, we aim to train existing XMC algorithms on both, the original and new training instances, leading to an average 5% relative improvements for 6 state-of-the-art algorithms across 4 benchmark datasets consisting of up to 1.3M labels. Gandalf can be applied in a plug-and-play manner to various methods and thus forwards the state-of-the-art in the domain, without incurring any additional computational overheads.

Consistent algorithms for multi-label classification with macro-at-$k$ metrics

We consider the optimization of complex performance metrics in multi-label classification under the population utility framework. We mainly focus on metrics linearly decomposable into a sum of binary classification utilities applied separately to each label with an additional requirement of exactly $k$ labels predicted for each instance. These "macro-at-$k$" metrics possess desired properties for extreme classification problems with long tail labels. Unfortunately, the at-$k$ constraint couples the otherwise independent binary classification tasks, leading to a much more challenging optimization problem than standard macro-averages. We provide a statistical framework to study this problem, prove the existence and the form of the optimal classifier, and propose a statistically consistent and practical learning algorithm based on the Frank-Wolfe method. Interestingly, our main results concern even more general metrics being non-linear functions of label-wise confusion matrices. Empirical results provide evidence for the competitive performance of the proposed approach.

Generalized test utilities for long-tail performance in extreme multi-label classification

Extreme multi-label classification (XMLC) is the task of selecting a small subset of relevant labels from a very large set of possible labels. As such, it is characterized by long-tail labels, i.e., most labels have very few positive instances. With standard performance measures such as precision@k, a classifier can ignore tail labels and still report good performance. However, it is often argued that correct predictions in the tail are more interesting or rewarding, but the community has not yet settled on a metric capturing this intuitive concept. The existing propensity-scored metrics fall short on this goal by confounding the problems of long-tail and missing labels. In this paper, we analyze generalized metrics budgeted "at k" as an alternative solution. To tackle the challenging problem of optimizing these metrics, we formulate it in the expected test utility (ETU) framework, which aims at optimizing the expected performance on a fixed test set. We derive optimal prediction rules and construct computationally efficient approximations with provable regret guarantees and robustness against model misspecification. Our algorithm, based on block coordinate ascent, scales effortlessly to XMLC problems and obtains promising results in terms of long-tail performance.

Towards Memory-Efficient Training for Extremely Large Output Spaces -- Learning with 500k Labels on a Single Commodity GPU

In classification problems with large output spaces (up to millions of labels), the last layer can require an enormous amount of memory. Using sparse connectivity would drastically reduce the memory requirements, but as we show below, it can result in much diminished predictive performance of the model. Fortunately, we found that this can be mitigated by introducing a penultimate layer of intermediate size. We further demonstrate that one can constrain the connectivity of the sparse layer to be uniform, in the sense that each output neuron will have the exact same number of incoming connections. This allows for efficient implementations of sparse matrix multiplication and connection redistribution on GPU hardware. Via a custom CUDA implementation, we show that the proposed approach can scale to datasets with 670,000 labels on a single commodity GPU with only 4GB memory.

Physics-guided adversarial networks for artificial digital image correlation data generation

Digital image correlation (DIC) has become a valuable tool in the evaluation of mechanical experiments, particularly fatigue crack growth experiments. The evaluation requires accurate information of the crack path and crack tip position, which is difficult to obtain due to inherent noise and artefacts. Machine learning models have been extremely successful in recognizing this relevant information given labelled DIC displacement data. For the training of robust models, which generalize well, big data is needed. However, data is typically scarce in the field of material science and engineering because experiments are expensive and time-consuming. We present a method to generate synthetic DIC displacement data using generative adversarial networks with a physics-guided discriminator. To decide whether data samples are real or fake, this discriminator additionally receives the derived von Mises equivalent strain. We show that this physics-guided approach leads to improved results in terms of visual quality of samples, sliced Wasserstein distance, and geometry score.

CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification

Extreme Multi-label Text Classification (XMC) involves learning a classifier that can assign an input with a subset of most relevant labels from millions of label choices. Recent approaches, such as XR-Transformer and LightXML, leverage a transformer instance to achieve state-of-the-art performance. However, in this process, these approaches need to make various trade-offs between performance and computational requirements. A major shortcoming, as compared to the Bi-LSTM based AttentionXML, is that they fail to keep separate feature representations for each resolution in a label tree. We thus propose CascadeXML, an end-to-end multi-resolution learning pipeline, which can harness the multi-layered architecture of a transformer model for attending to different label resolutions with separate feature representations. CascadeXML significantly outperforms all existing approaches with non-trivial gains obtained on benchmark datasets consisting of up to three million labels. Code for CascadeXML will be made publicly available at \url{https://github.com/xmc-aalto/cascadexml}.

On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification

The propensity model introduced by Jain et al. 2016 has become a standard approach for dealing with missing and long-tail labels in extreme multi-label classification (XMLC). In this paper, we critically revise this approach showing that despite its theoretical soundness, its application in contemporary XMLC works is debatable. We exhaustively discuss the flaws of the propensity-based approach, and present several recipes, some of them related to solutions used in search engines and recommender systems, that we believe constitute promising alternatives to be followed in XMLC.

Speeding-up One-vs-All Training for Extreme Classification via Smart Initialization

In this paper we show that a simple, data dependent way of setting the initial vector can be used to substantially speed up the training of linear one-versus-all (OVA) classifiers in extreme multi-label classification (XMC). We discuss the problem of choosing the initial weights from the perspective of three goals. We want to start in a region of weight space a) with low loss value, b) that is favourable for second-order optimization, and c) where the conjugate-gradient (CG) calculations can be performed quickly. For margin losses, such an initialization is achieved by selecting the initial vector such that it separates the mean of all positive (relevant for a label) instances from the mean of all negatives -- two quantities that can be calculated quickly for the highly imbalanced binary problems occurring in XMC. We demonstrate a speedup of $\approx 3\times$ for training with squared hinge loss on a variety of XMC datasets. This comes in part from the reduced number of iterations that need to be performed due to starting closer to the solution, and in part from an implicit negative mining effect that allows to ignore easy negatives in the CG step. Because of the convex nature of the optimization problem, the speedup is achieved without any degradation in classification accuracy.