Extreme multi-label classification (XMC) seeks to find relevant labels from an extremely large label collection for a given text input. To tackle such a vast label space, current state-of-the-art methods fall into two categories. The oneversus-all (OVA) method uses learnable label embeddings for each label, excelling at memorization (i.e., capturing detailed training signals for accurate head label prediction). In contrast, the dual-encoder (DE) model maps input and label text into a shared embedding space for better generalization (i.e., the capability of predicting tail labels with limited training data), but may fall short at memorization. To achieve generalization and memorization, existing XMC methods often combine DE and OVA models, which involves complex training pipelines. Inspired by the success of retrieval-augmented language models, we propose the Retrieval-augmented Encoders for XMC (RAE-XMC), a novel framework that equips a DE model with retrieval-augmented capability for efficient memorization without additional trainable parameter. During training, RAE-XMC is optimized by the contrastive loss over a knowledge memory that consists of both input instances and labels. During inference, given a test input, RAE-XMC retrieves the top-K keys from the knowledge memory, and aggregates the corresponding values as the prediction scores. RAE-XMC not only advances the state-of-the-art (SOTA) DE method DEXML Gupta et al. (2024), but also achieves more than 10x speedup on the largest LF-AmazonTitles-1.3M dataset under the same 8 A100 GPUs training environments.

Current brain surface-based prediction models often overlook the variability of regional attributes at the cortical feature level. While graph neural networks (GNNs) excel at capturing regional differences, they encounter challenges when dealing with complex, high-density graph structures. In this work, we consider the cortical surface mesh as a sparse graph and propose an interpretable prediction model-Surface Graph Neural Network (SurfGNN). SurfGNN employs topology-sampling learning (TSL) and region-specific learning (RSL) structures to manage individual cortical features at both lower and higher scales of the surface mesh, effectively tackling the challenges posed by the overly abundant mesh nodes and addressing the issue of heterogeneity in cortical regions. Building on this, a novel score-weighted fusion (SWF) method is implemented to merge nodal representations associated with each cortical feature for prediction. We apply our model to a neonatal brain age prediction task using a dataset of harmonized MR images from 481 subjects (503 scans). SurfGNN outperforms all existing state-of-the-art methods, demonstrating an improvement of at least 9.0% and achieving a mean absolute error (MAE) of 0.827+0.056 in postmenstrual weeks. Furthermore, it generates feature-level activation maps, indicating its capability to identify robust regional variations in different morphometric contributions for prediction.

Embedding-based Retrieval Models (ERMs) have emerged as a promising framework for large-scale text retrieval problems due to powerful large language models. Nevertheless, fine-tuning ERMs to reach state-of-the-art results can be expensive due to the extreme scale of data as well as the complexity of multi-stages pipelines (e.g., pre-training, fine-tuning, distillation). In this work, we propose the PEFA framework, namely ParamEter-Free Adapters, for fast tuning of ERMs without any backward pass in the optimization. At index building stage, PEFA equips the ERM with a non-parametric k-nearest neighbor (kNN) component. At inference stage, PEFA performs a convex combination of two scoring functions, one from the ERM and the other from the kNN. Based on the neighborhood definition, PEFA framework induces two realizations, namely PEFA-XL (i.e., extra large) using double ANN indices and PEFA-XS (i.e., extra small) using a single ANN index. Empirically, PEFA achieves significant improvement on two retrieval applications. For document retrieval, regarding Recall@100 metric, PEFA improves not only pre-trained ERMs on Trivia-QA by an average of 13.2%, but also fine-tuned ERMs on NQ-320K by an average of 5.5%, respectively. For product search, PEFA improves the Recall@100 of the fine-tuned ERMs by an average of 5.3% and 14.5%, for PEFA-XS and PEFA-XL, respectively. Our code is available at https://github.com/amzn/pecos/tree/mainline/examples/pefa-wsdm24.

We introduce a novel class of sample-based explanations we term high-dimensional representers, that can be used to explain the predictions of a regularized high-dimensional model in terms of importance weights for each of the training samples. Our workhorse is a novel representer theorem for general regularized high-dimensional models, which decomposes the model prediction in terms of contributions from each of the training samples: with positive (negative) values corresponding to positive (negative) impact training samples to the model's prediction. We derive consequences for the canonical instances of $\ell_1$ regularized sparse models, and nuclear norm regularized low-rank models. As a case study, we further investigate the application of low-rank models in the context of collaborative filtering, where we instantiate high-dimensional representers for specific popular classes of models. Finally, we study the empirical performance of our proposed methods on three real-world binary classification datasets and two recommender system datasets. We also showcase the utility of high-dimensional representers in explaining model recommendations.

The eXtreme Multi-label Classification~(XMC) problem seeks to find relevant labels from an exceptionally large label space. Most of the existing XMC learners focus on the extraction of semantic features from input query text. However, conventional XMC studies usually neglect the side information of instances and labels, which can be of use in many real-world applications such as recommendation systems and e-commerce product search. We propose Predicted Instance Neighborhood Aggregation (PINA), a data enhancement method for the general XMC problem that leverages beneficial side information. Unlike most existing XMC frameworks that treat labels and input instances as featureless indicators and independent entries, PINA extracts information from the label metadata and the correlations among training instances. Extensive experimental results demonstrate the consistent gain of PINA on various XMC tasks compared to the state-of-the-art methods: PINA offers a gain in accuracy compared to standard XR-Transformers on five public benchmark datasets. Moreover, PINA achieves a $\sim 5\%$ gain in accuracy on the largest dataset LF-AmazonTitles-1.3M. Our implementation is publicly available.

Extreme multi-label text classification (XMC) seeks to find relevant labels from an extreme large label collection for a given text input. Many real-world applications can be formulated as XMC problems, such as recommendation systems, document tagging and semantic search. Recently, transformer based XMC methods, such as X-Transformer and LightXML, have shown significant improvement over other XMC methods. Despite leveraging pre-trained transformer models for text representation, the fine-tuning procedure of transformer models on large label space still has lengthy computational time even with powerful GPUs. In this paper, we propose a novel recursive approach, XR-Transformer to accelerate the procedure through recursively fine-tuning transformer models on a series of multi-resolution objectives related to the original XMC objective function. Empirical results show that XR-Transformer takes significantly less training time compared to other transformer-based XMC models while yielding better state-of-the-art results. In particular, on the public Amazon-3M dataset with 3 million labels, XR-Transformer is not only 20x faster than X-Transformer but also improves the Precision@1 from 51% to 54%.

Deep neural networks have yielded superior performance in many applications; however, the gradient computation in a deep model with millions of instances leads to a lengthy training process even with modern GPU/TPU hardware acceleration. In this paper, we propose AutoAssist, a simple framework to accelerate training of a deep neural network. Typically, as the training procedure evolves, the amount of improvement in the current model by a stochastic gradient update on each instance varies dynamically . In AutoAssist, we utilize this fact and design a simple instance shrinking operation, which is used to filter out instances with relatively low marginal improvement to the current model; thus the computationally intensive gradient computations are performed on informative instances as much as possible. We prove that the proposed technique outperforms vanilla SGD with existing importance sampling approaches for linear SVM problems, and establish an O(1/k) convergence for strongly convex problems. In order to apply the proposed techniques to accelerate training of deep models, we propose to jointly train a very lightweight Assistant network in addition to the original deep network referred to as Boss. The Assistant network is designed to gauge the importance of a given instance with respect to the current Boss such that a shrinking operation can be applied in the batch generator. With careful design, we train the Boss and Assistant in a nonblocking and asynchronous fashion such that overhead is minimal. We demonstrate that AutoAssist reduces the number of epochs by 40% for training a ResNet to reach the same test accuracy on an image classification data set, and saves 30% training time needed for a transformer model to yield the same BLEU scores on a translation dataset.

Vanishing and exploding gradients are two of the main obstacles in training deep neural networks, especially in capturing long range dependencies in recurrent neural networks~(RNNs). In this paper, we present an efficient parametrization of the transition matrix of an RNN that allows us to stabilize the gradients that arise in its training. Specifically, we parameterize the transition matrix by its singular value decomposition(SVD), which allows us to explicitly track and control its singular values. We attain efficiency by using tools that are common in numerical linear algebra, namely Householder reflectors for representing the orthogonal matrices that arise in the SVD. By explicitly controlling the singular values, our proposed Spectral-RNN method allows us to easily solve the exploding gradient problem and we observe that it empirically solves the vanishing gradient issue to a large extent. We note that the SVD parameterization can be used for any rectangular weight matrix, hence it can be easily extended to any deep neural network, such as a multi-layer perceptron. Theoretically, we demonstrate that our parameterization does not lose any expressive power, and show how it controls generalization of RNN for the classification task. %, and show how it potentially makes the optimization process easier. Our extensive experimental results also demonstrate that the proposed framework converges faster, and has good generalization, especially in capturing long range dependencies, as shown on the synthetic addition and copy tasks, as well as on MNIST and Penn Tree Bank data sets.

It is a known fact that training recurrent neural networks for tasks that have long term dependencies is challenging. One of the main reasons is the vanishing or exploding gradient problem, which prevents gradient information from propagating to early layers. In this paper we propose a simple recurrent architecture, the Fourier Recurrent Unit (FRU), that stabilizes the gradients that arise in its training while giving us stronger expressive power. Specifically, FRU summarizes the hidden states $h^{(t)}$ along the temporal dimension with Fourier basis functions. This allows gradients to easily reach any layer due to FRU's residual learning structure and the global support of trigonometric functions. We show that FRU has gradient lower and upper bounds independent of temporal dimension. We also show the strong expressivity of sparse Fourier basis, from which FRU obtains its strong expressive power. Our experimental study also demonstrates that with fewer parameters the proposed architecture outperforms other recurrent architectures on many tasks.

We propose extreme stochastic variational inference (ESVI), an asynchronous and lock-free algorithm to perform variational inference on massive real world datasets. Stochastic variational inference (SVI), the state-of-the-art algorithm for scaling variational inference to large-datasets, is inherently serial. Moreover, it requires the parameters to fit in the memory of a single processor; this is problematic when the number of parameters is in billions. ESVI overcomes these limitations by requiring that each processor only access a subset of the data and a subset of the parameters, thus providing data and model parallelism simultaneously. We demonstrate the effectiveness of ESVI by running Latent Dirichlet Allocation (LDA) on UMBC-3B, a dataset that has a vocabulary of 3 million and a token size of 3 billion. To best of our knowledge, this is an order of magnitude larger than the largest dataset on which results using variational inference have been reported in literature. In our experiments, we found that ESVI outperforms VI and SVI, and also achieves a better quality solution. In addition, we propose a strategy to speed up computation and save memory when fitting large number of topics.