Multi-Task Learning

We study deep neural networks for the multi-label classification (MLab) task through the lens of neural collapse (NC). Previous works have been restricted to the multi-class classification setting and discovered a prevalent NC phenomenon comprising of the following properties for the last-layer features: (i) the variability of features within every class collapses to zero, (ii) the set of feature means form an equi-angular tight frame (ETF), and (iii) the last layer classifiers collapse to the feature mean upon some scaling. We generalize the study to multi-label learning, and prove for the first time that a generalized NC phenomenon holds with the "pick-all-label'' formulation, which we term as MLab NC. While the ETF geometry remains consistent for features with a single label, multi-label scenarios introduce a unique combinatorial aspect we term the "tag-wise average" property, where the means of features with multiple labels are the scaled averages of means for single-label instances. Theoretically, under proper assumptions on the features, we establish that the only global optimizer of the pick-all-label cross-entropy loss satisfy the multi-label NC. In practice, we demonstrate that our findings can lead to better test performance with more efficient training techniques for MLab learning.

Prompt-based learning has been demonstrated as a compelling paradigm contributing to large language models' tremendous success (LLMs). Inspired by their success in language tasks, existing research has leveraged LLMs in embodied instruction following and task planning. In this work, we tackle the problem of training a robot to understand multimodal prompts, interleaving vision signals with text descriptions. This type of task poses a major challenge to robots' capability to understand the interconnection and complementarity between vision and language signals. In this work, we introduce an effective framework that learns a policy to perform robot manipulation with multimodal prompts from multi-task expert trajectories. Our methods consist of a two-stage training pipeline that performs inverse dynamics pretraining and multi-task finetuning. To facilitate multimodal understanding, we design our multimodal prompt encoder by augmenting a pretrained LM with a residual connection to the visual input and model the dependencies among action dimensions. Empirically, we evaluate the efficacy of our method on the VIMA-BENCH and establish a new state-of-the-art (10% improvement in success rate). Moreover, we demonstrate that our model exhibits remarkable in-context learning ability.

The abundance of free internet data offers unprecedented opportunities for researchers and developers, but it also poses privacy risks. Utilizing data without explicit consent raises critical challenges in protecting personal information.Unlearnable examples have emerged as a feasible protection approach, which renders the data unlearnable, i.e., useless to third parties, by injecting imperceptible perturbations. However, these perturbations only exhibit unlearnable effects on either a particular dataset or label-consistent scenarios, thereby lacking broad applicability. To address both issues concurrently, we propose a universal perturbation generator that harnesses data with concept unlearnability, thereby broadening the scope of unlearnability beyond specific datasets or labels. Specifically, we leverage multi-modal pre-trained models to establish a connection between the data concepts in a shared embedding space. This connection enables the information transformation from image data to text concepts. Consequently, we can align the text embedding using concept-wise discriminant loss, and render the data unlearnable. Extensive experiments conducted on real-world datasets demonstrate the concept unlearnability, i.e., cross-dataset transferability and label-agnostic utility, of our proposed unlearnable examples, as well as their robustness against attacks.

We study how representation learning can improve the learning efficiency of contextual bandit problems. We study the setting where we play T linear contextual bandits with dimension simultaneously, and these T bandit tasks collectively share a common linear representation with a dimensionality of r ≪ d. We present a new algorithm based on alternating projected gradient descent (GD) and minimization estimator to recover a low-rank feature matrix. We obtain constructive provable guarantees for our estimator that provide a lower bound on the required sample complexity and an upper bound on the iteration complexity (total number of iterations needed to achieve a certain error level). Using the proposed estimator, we present a multi-task learning algorithm for linear contextual bandits and prove the regret bound of our algorithm. We presented experiments and compared the performance of our algorithm against benchmark algorithms.

Multi-view clustering has been widely explored for its effectiveness in harmonizing heterogeneity along with consistency in different views of data. Despite the significant progress made by recent works, the performance of most existing methods is heavily reliant on strong priori information regarding the true cluster number $\textit{K}$, which is rarely feasible in real-world scenarios. In this paper, we propose a novel graph-based multi-view clustering algorithm to infer unknown $\textit{K}$ through a graph consistency reward mechanism. To be specific, we evaluate the cluster indicator matrix during each iteration with respect to diverse $\textit{K}$. We formulate the inference process of unknown $\textit{K}$ as a parsimonious reinforcement learning paradigm, where the reward is measured by inter-cluster connectivity. As a result, our approach is capable of independently producing the final clustering result, free from the input of a predefined cluster number. Experimental results on multiple benchmark datasets demonstrate the effectiveness of our proposed approach in comparison to existing state-of-the-art methods.

Continual learning (CL) aims to learn from sequentially arriving tasks without catastrophic forgetting (CF). By partitioning the network into two parts based on the Lottery Ticket Hypothesis---one for holding the knowledge of the old tasks while the other for learning the knowledge of the new task---the recent progress has achieved forget-free CL. Although addressing the CF issue well, such methods would encounter serious under-fitting in long-term CL, in which the learning process will continue for a long time and the number of new tasks involved will be much higher. To solve this problem, this paper partitions the network into three parts---with a new part for exploring the knowledge sharing between the old and new tasks. With the shared knowledge, this part of network can be learnt to simultaneously consolidate the old tasks and fit to the new task. To achieve this goal, we propose a task-aware **Orthogonal Sparse Network** (OSN), which contains shared knowledge induced network partition and sharpness-aware orthogonal sparse network learning. The former partitions the network to select shared parameters, while the latter guides the exploration of shared knowledge through shared parameters. Qualitative and quantitative analyses, show that the proposed OSN induces minimum to no interference with past tasks, *i.e.*, approximately no forgetting, while greatly improves the model plasticity and capacity, and finally achieves the state-of-the-art performances.

Recent years have experienced increasing utilization of complex machine learning models across multiple sources of data to inform more generalizable decision-making. However, distribution shifts across data sources and privacy concerns related to sharing individual-level data, coupled with a lack of uncertainty quantification from machine learning predictions, make it challenging to achieve valid inferences in multi-source environments. In this paper, we consider the problem of obtaining distribution-free prediction intervals for a target population, leveraging multiple potentially biased data sources. We derive the efficient influence functions for the quantiles of unobserved outcomes in the target and source populations, and show that one can incorporate machine learning prediction algorithms in the estimation of nuisance functions while still achieving parametric rates of convergence to nominal coverage probabilities. Moreover, when conditional outcome invariance is violated, we propose a data-adaptive strategy to upweight informative data sources for efficiency gain and downweight non-informative data sources for bias reduction. We highlight the robustness and efficiency of our proposals for a variety of conformal scores and data-generating mechanisms via extensive synthetic experiments. Hospital length of stay prediction intervals for pediatric patients undergoing a high-risk cardiac surgical procedure between 2016-2022 in the U.S. illustrate the utility of our methodology.

The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning. In this work, we discover an intriguing linear phenomenon in models that are initialized from a common pretrained checkpoint and finetuned on different tasks, termed as Cross-Task Linearity (CTL). Specifically, we show that if we linearly interpolate the weights of two finetuned models, the features in the weight-interpolated model are often approximately equal to the linear interpolation of features in two finetuned models at each layer. We provide comprehensive empirical evidence supporting that CTL consistently occurs for finetuned models that start from the same pretrained checkpoint. We conjecture that in the pretraining-finetuning paradigm, neural networks approximately function as linear maps, mapping from the parameter space to the feature space. Based on this viewpoint, our study unveils novel insights into explaining model merging/editing, particularly by translating operations from the parameter space to the feature space. Furthermore, we delve deeper into the root cause for the emergence of CTL, highlighting the role of pretraining.

Aligning image pairs captured by different sensors or those undergoing significant appearance changes is crucial for various computer vision and robotics applications. Existing approaches cope with this problem via either Sparse feature Matching (SM) or Dense direct Alignment (DA) paradigms. Sparse methods are efficient but lack accuracy in textureless scenes, while dense ones are more accurate in all scenes but demand for good initialization. In this paper, we propose SDME, a Sparse-to-Dense Multimodal feature Extractor based on a novel multi-task network that simultaneously predicts SM and DA features for robust multimodal image registration. We propose the sparse-to-dense registration paradigm: we first perform initial registration via SM and then refine the result via DA. By using the well-designed SDME, the sparse-to-dense approach combines the merits from both SM and DA. Extensive experiments on MSCOCO, GoogleEarth, VIS-NIR and VIS-IR-drone datasets demonstrate that our method achieves remarkable performance on multimodal cases. Furthermore, our approach exhibits robust generalization capabilities, enabling the fine-tuning of models initially trained on single-modal datasets for use with smaller multimodal datasets. Our code is available at https://github.com/KN-Zhang/SDME.

Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs), where improving performance on unseen tasks often leads to a significant performance drop on the original tasks. This paper presents a comprehensive analysis of catastrophic forgetting in MLLMs and introduces a post-training adjustment method called Model Tailor. Our method primarily preserves the pre-trained parameters while replacing a small number ($\leq$ 10%) of fine-tuned parameters, maintaining $\sim$ 99% effectiveness on original tasks versus pre-training, and achieving $\sim$ 97% on new tasks compared to standard fine-tuning. Specifically, we derive a sparse mask to identify the model patch, based on a fusion strategy that integrates salience and sensitivity analysis. Subsequently, a compensation mechanism is introduced to decorate the patch, enhancing the model's performance on both target and original tasks. Additionally, our method is adaptable to multi-task scenarios. Through extensive experiments on InstructBLIP and LLaVA-1.5 in both image captioning and visual question answering tasks, our approach demonstrates significant task adaptability while preserving inherent pre-trained capabilities.

Large language models such as GPT and Llama are trained with a next-token prediction loss. In this work, we suggest that training language models to predict multiple future tokens at once results in higher sample efficiency. More specifically, at each position in the training corpus, we ask the model to predict the following $n$ tokens using $n$ independent output heads, operating on top of a shared model trunk. Considering multi-token prediction as an auxiliary training task, we measure improved downstream capabilities with no overhead in training time for both code and natural language models. The method is increasingly useful for larger model sizes, and keeps its appeal when training for multiple epochs. Gains are especially pronounced on generative benchmarks like coding, where our models consistently outperform strong baselines by several percentage points. Our 13B parameter models solves 12% more problems on Human Eval and 17% more on MBPP than comparable next-token models. Experiments on small algorithmic tasks demonstrate that multi-token prediction is favorable for the development of induction heads and algorithmic reasoning capabilities. As an additional benefit, models trained with 4-token prediction are up to $3\times$ faster at inference, even with large batch sizes.

An array of recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such linear representations. To that end, we introduce a latent variable model to abstract and formalize the concept dynamics of the next token prediction. We use this formalism to prove that linearity arises as a consequence of the loss function and the implicit bias of gradient descent. The theory is further substantiated empirically via experiments.

Merging various task-specific Transformer-based vision models trained on different tasks into a single unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have been proven to be both effective and scalable. Existing methods have primarily focused on seeking a static optimal solution within the original model parameter space. A notable challenge is mitigating the interference between parameters of different models, which can substantially deteriorate performance. In this paper, we propose to merge most of the parameters while upscaling the MLP of the Transformer layers to a weight-ensembling mixture of experts (MoE) module, which can dynamically integrate shared and task-specific knowledge based on the input, thereby providing a more flexible solution that can adapt to the specific needs of each instance. Our key insight is that by identifying and separating shared knowledge and task-specific knowledge, and then dynamically integrating them, we can mitigate the parameter interference problem to a great extent. We conduct the conventional multi-task model merging experiments and evaluate the generalization and robustness of our method. The results demonstrate the effectiveness of our method and provide a comprehensive understanding of our method. The code is available at https://github.com/tanganke/weight-ensembling_MoE

Learning to solve vehicle routing problems (VRPs) has garnered much attention. However, most neural solvers are only structured and trained independently on a specific problem, making them less generic and practical. In this paper, we aim to develop a unified neural solver that can cope with a range of VRP variants simultaneously. Specifically, we propose a multi-task vehicle routing solver with mixture-of-experts (MVMoE), which greatly enhances the model capacity without a proportional increase in computation. We further develop a hierarchical gating mechanism for the MVMoE, delivering a good trade-off between empirical performance and computational complexity. Experimentally, our method significantly promotes zero-shot generalization performance on 10 unseen VRP variants, and showcases decent results on the few-shot setting and real-world benchmark instances. We further conduct extensive studies on the effect of MoE configurations in solving VRPs, and observe the superiority of hierarchical gating when facing out-of-distribution data. The source code is available at: https://github.com/RoyalSkye/Routing-MVMoE.

We aim to address Multi-Task Learning (MTL) with a large number of tasks by Multi-Task Grouping (MTG). Given $N$ tasks, we propose to **simultaneously identify the best task groups from $2^N$ candidates and train the model weights simultaneously in one-shot**, with **the high-order task-affinity fully exploited**. This is distinct from the pioneering methods which sequentially identify the groups and train the model weights, where the group identification often relies on heuristics. As a result, our method not only improves the training efficiency, but also mitigates the objective bias introduced by the sequential procedures that potentially leads to a suboptimal solution. Specifically, **we formulate MTG as a fully differentiable pruning problem on an adaptive network architecture determined by an unknown Categorical distribution**. To categorize $N$ tasks into $K$ groups (represented by $K$ encoder branches), we initially set up $KN$ task heads, where each branch connects to all $N$ task heads to exploit the high-order task-affinity. Then, we gradually prune the $KN$ heads down to $N$ by learning a relaxed differentiable Categorical distribution, ensuring that each task is exclusively and uniquely categorized into only one branch. Extensive experiments on CelebA and Taskonomy datasets with detailed ablations show the promising performance and efficiency of our method. The codes are available at https://github.com/ethanygao/DMTG.

The multi-group learning model formalizes the learning scenario in which a single predictor must generalize well on multiple, possibly overlapping subgroups of interest. We extend the study of multi-group learning to the natural case where the groups are hierarchically structured. We design an algorithm for this setting that outputs an interpretable and deterministic decision tree predictor with near-optimal sample complexity. We then conduct an empirical evaluation of our algorithm and find that it achieves attractive generalization properties on real datasets with hierarchical group structure.

Autoencoders have become an indispensable tool for generative modeling and representation learning in high dimensions. Imposing structural constraints such as conditional independence in order to capture invariance of latent variables to nuisance information has been attempted through adding *ad hoc* penalties to the loss function mostly in the variational autoencoder (VAE) context, often based on heuristics. This paper demonstrates that Wasserstein autoencoders (WAEs) are highly flexible in embracing such structural constraints. Well-known extensions of VAEs for this purpose are gracefully handled within the framework of WAEs. In particular, given a conditional independence structure of the generative model (decoder), corresponding encoder structure and penalties are derived from the functional constraints that define the WAE. These structural uses of WAEs, termed StrWAEs (“stairways”), open up a principled way of penalizing autoencoders to impose structural constraints. Utilizing these advantages, we present handful of results on semi-supervised classification, conditional generation, and invariant representation tasks.

Active learning is increasingly adopted for expensive multi-objective combinatorial optimization problems, but it involves a challenging subset selection problem, optimizing the batch acquisition score that quantifies the goodness of a batch for evaluation. Due to the excessively large search space of the subset selection problem, prior methods optimize the batch acquisition on the latent space, which has discrepancies with the actual space, or optimize individual acquisition scores without considering the dependencies among candidates in a batch instead of directly optimizing the batch acquisition. To manage the vast search space, a simple and effective approach is the greedy method, which decomposes the problem into smaller subproblems, yet it has difficulty in parallelization since each subproblem depends on the outcome from the previous ones. To this end, we introduce a novel greedy-style subset selection algorithm that optimizes batch acquisition directly on the combinatorial space by sequential greedy sampling from the greedy policy, specifically trained to address all greedy subproblems concurrently. Notably, our experiments on the red fluorescent proteins design task show that our proposed method achieves the baseline performance in 1.69x fewer queries, demonstrating its efficiency.

In this paper, we study hybrid neural representations for spherical data, a domain of increasing relevance in scientific research. In particular, our work focuses on weather and climate data as well as cosmic microwave background (CMB) data. Although previous studies have delved into coordinate-based neural representations for spherical signals, they often fail to capture the intricate details of highly nonlinear signals. To address this limitation, we introduce a novel approach named Hybrid Neural Representations for Spherical data (HNeR-S). Our main idea is to use spherical feature-grids to obtain positional features which are combined with a multi-layer perceptron to predict the target signal. We consider feature-grids with equirectangular and hierarchical equal area isolatitude pixelization structures that align with weather data and CMB data, respectively. We extensively verify the effectiveness of our HNeR-S for regression, super-resolution, temporal interpolation, and compression tasks.

In this paper, we investigate a Multi-Armed Bandit (MAB) setting where an arm exits the game if the algorithm continuously neglects it. This setup is motivated by real-world scenarios, such as online advertising and crowdsourcing, where arms only gain benefits after being pulled by the algorithm. We identify the intrinsic hardness of this problem and limitations in existing approaches. We propose FC-SE algorithm with expected regret upper bounds as our solution to this problem. As an extension, we even allow new arms to enter after the game starts and design FC-Entry algorithm with performance guarantees for this setup. Finally, we conduct experiments to validate our theoretical results.