Regression models often fail to generalize effectively in regions characterized by highly imbalanced label distributions. Previous methods for deep imbalanced regression rely on gradient-based weight updates, which tend to overfit in underrepresented regions. This paper proposes a paradigm shift towards in-context learning as an effective alternative to conventional in-weight learning methods, particularly for addressing imbalanced regression. In-context learning refers to the ability of a model to condition itself, given a prompt sequence composed of in-context samples (input-label pairs) alongside a new query input to generate predictions, without requiring any parameter updates. In this paper, we study the impact of the prompt sequence on the model performance from both theoretical and empirical perspectives. We emphasize the importance of localized context in reducing bias within regions of high imbalance. Empirical evaluations across a variety of real-world datasets demonstrate that in-context learning substantially outperforms existing in-weight learning methods in scenarios with high levels of imbalance.

The evaluation of machine learning models using human-labeled validation data can be expensive and time-consuming. AI-labeled synthetic data can be used to decrease the number of human annotations required for this purpose in a process called autoevaluation. We suggest efficient and statistically principled algorithms for this purpose that improve sample efficiency while remaining unbiased. These algorithms increase the effective human-labeled sample size by up to 50% on experiments with GPT-4.

The rapid growth of neural network models shared on the internet has made model weights an important data modality. However, this information is underutilized as the weights are uninterpretable, and publicly available models are disorganized. Inspired by Darwin's tree of life, we define the Model Tree which describes the origin of models i.e., the parent model that was used to fine-tune the target model. Similarly to the natural world, the tree structure is unknown. In this paper, we introduce the task of Model Tree Heritage Recovery (MoTHer Recovery) for discovering Model Trees in the ever-growing universe of neural networks. Our hypothesis is that model weights encode this information, the challenge is to decode the underlying tree structure given the weights. Beyond the immediate application of model authorship attribution, MoTHer recovery holds exciting long-term applications akin to indexing the internet by search engines. Practically, for each pair of models, this task requires: i) determining if they are related, and ii) establishing the direction of the relationship. We find that certain distributional properties of the weights evolve monotonically during training, which enables us to classify the relationship between two given models. MoTHer recovery reconstructs entire model hierarchies, represented by a directed tree, where a parent model gives rise to multiple child models through additional training. Our approach successfully reconstructs complex Model Trees, as well as the structure of "in-the-wild" model families such as Llama 2 and Stable Diffusion.

Personalized Federated Learning (PFL) is proposed to find the greatest personalized models for each client. To avoid the central failure and communication bottleneck in the server-based FL, we concentrate on the Decentralized Personalized Federated Learning (DPFL) that performs distributed model training in a Peer-to-Peer (P2P) manner. Most personalized works in DPFL are based on undirected and symmetric topologies, however, the data, computation and communication resources heterogeneity result in large variances in the personalized models, which lead the undirected aggregation to suboptimal personalized performance and unguaranteed convergence. To address these issues, we propose a directed collaboration DPFL framework by incorporating stochastic gradient push and partial model personalized, called \textbf{D}ecentralized \textbf{Fed}erated \textbf{P}artial \textbf{G}radient \textbf{P}ush (\textbf{DFedPGP}). It personalizes the linear classifier in the modern deep model to customize the local solution and learns a consensus representation in a fully decentralized manner. Clients only share gradients with a subset of neighbors based on the directed and asymmetric topologies, which guarantees flexible choices for resource efficiency and better convergence. Theoretically, we show that the proposed DFedPGP achieves a superior convergence rate of $\mathcal{O}(\frac{1}{\sqrt{T}})$ in the general non-convex setting, and prove the tighter connectivity among clients will speed up the convergence. The proposed method achieves state-of-the-art (SOTA) accuracy in both data and computation heterogeneity scenarios, demonstrating the efficiency of the directed collaboration and partial gradient push.

Low-rank adaptation (LoRA) has become the standard approach for parameter-efficient fine-tuning of large language models (LLM), but our theoretical understanding of LoRA has been limited. In this work, we theoretically analyze LoRA fine-tuning in the neural tangent kernel (NTK) regime with $N$ data points, showing: (i) full fine-tuning (without LoRA) admits a low-rank solution of rank $r\lesssim \sqrt{N}$; (ii) using LoRA with rank $r\gtrsim \sqrt{N}$ eliminates spurious local minima, allowing gradient descent to find the low-rank solutions; (iii) the low-rank solution found using LoRA generalizes well.

Topic models have been evolving rapidly over the years, from conventional to recent neural models. However, existing topic models generally struggle with either effectiveness, efficiency, or stability, highly impeding their practical applications. In this paper, we propose FASTopic, a fast, adaptive, stable, and transferable topic model. FASTopic follows a new paradigm: Dual Semantic-relation Reconstruction (DSR). Instead of previous conventional, neural VAE-based or clustering-based methods, DSR discovers latent topics by reconstruction through modeling the semantic relations among document, topic, and word embeddings. This brings about a neat and efficient topic modeling framework. We further propose a novel Embedding Transport Plan (ETP) method. Rather than early straightforward approaches, ETP explicitly regularizes the semantic relations as optimal transport plans. This addresses the relation bias issue and thus leads to effective topic modeling. Extensive experiments on benchmark datasets demonstrate that our FASTopic shows superior effectiveness, efficiency, adaptivity, stability, and transferability, compared to state-of-the-art baselines across various scenarios. Our code is available at https://github.com/bobxwu/FASTopic .

Machine learning (ML) methods have experienced significant growth in the past decade, yet their practical application in high-impact real-world domains has been hindered by their opacity. When ML methods are responsible for making critical decisions, stakeholders often require insights into how to alter these decisions. Counterfactual explanations (CFEs) have emerged as a solution, offering interpretations of opaque ML models and providing a pathway to transition from one decision to another. However, most existing CFE methods require access to the model's training dataset, few methods can handle multivariate time-series, and none can handle multivariate time-series without training datasets. These limitations can be formidable in many scenarios. In this paper, we present CFWoT, a novel reinforcement-learning-based CFE method that generates CFEs when training datasets are unavailable. CFWoT is model-agnostic and suitable for both static and multivariate time-series datasets with continuous and discrete features. Users have the flexibility to specify non-actionable, immutable, and preferred features, as well as causal constraints which CFWoT guarantees will be respected. We demonstrate the performance of CFWoT against four baselines on several datasets and find that, despite not having access to a training dataset, CFWoT finds CFEs that make significantly fewer and significantly smaller changes to the input time-series. These properties make CFEs more actionable, as the magnitude of change required to alter an outcome is vastly reduced.

To generate summaries that include multiple aspects or topics for text documents, most approaches use clustering or topic modeling to group relevant sentences and then generate a summary for each group. These approaches struggle to optimize the summarization and clustering algorithms jointly. On the other hand, aspect-based summarization requires known aspects. Our solution integrates topic discovery and summarization into a single step. Given text data, our Joint Aspect Discovery and Summarization algorithm (JADS) discovers aspects from the input and generates a summary of the topics, in one step. We propose a self-supervised framework that creates a labeled dataset by first mixing sentences from multiple documents (e.g., CNN/DailyMail articles) as the input and then uses the article summaries from the mixture as the labels. The JADS model outperforms the two-step baselines. With pretraining, the model achieves better performance and stability. Furthermore, embeddings derived from JADS exhibit superior clustering capabilities. Our proposed method achieves higher semantic alignment with ground truth and is factual.

Federated learning (FL) was recently proposed to securely train models with data held over multiple locations ("clients") under the coordination of a central server. Two major challenges hindering the performance of FL algorithms are long training times caused by straggling clients, and a decline in model accuracy under non-iid local data distributions ("client drift"). In this work, we propose and analyze AsynchRonous Exact Averaging (AREA), a new stochastic (sub)gradient algorithm that utilizes asynchronous communication to speed up convergence and enhance scalability, and employs client memory to correct the client drift caused by variations in client update frequencies. Moreover, AREA is, to the best of our knowledge, the first method that is guaranteed to converge under arbitrarily long delays, without the use of delay-adaptive stepsizes, and (i) for strongly convex, smooth functions, asymptotically converges to an error neighborhood whose size depends only on the variance of the stochastic gradients used with respect to the number of iterations, and (ii) for convex, non-smooth functions, matches the convergence rate of the centralized stochastic subgradient method up to a constant factor, which depends on the average of the individual client update frequencies instead of their minimum (or maximum). Our numerical results validate our theoretical analysis and indicate AREA outperforms state-of-the-art methods when local data are highly non-iid, especially as the number of clients grows.

Deep metric learning (DML) involves training a network to learn a semantically meaningful representation space. Many current approaches mine n-tuples of examples and model interactions within each tuplets. We present a novel, compositional DML model, inspired by electrostatic fields in physics that, instead of in tuples, represents the influence of each example (embedding) by a continuous potential field, and superposes the fields to obtain their combined global potential field. We use attractive/repulsive potential fields to represent interactions among embeddings from images of the same/different classes. Contrary to typical learning methods, where mutual influence of samples is proportional to their distance, we enforce reduction in such influence with distance, leading to a decaying field. We show that such decay helps improve performance on real world datasets with large intra-class variations and label noise. Like other proxy-based methods, we also use proxies to succinctly represent sub-populations of examples. We evaluate our method on three standard DML benchmarks- Cars-196, CUB-200-2011, and SOP datasets where it outperforms state-of-the-art baselines.