论文检索

Miscellaneous Aspects of Machine Learning · Supervised Learning

KuanYu Chen, Ping-Han Chiang, Hsin-Rung Chou, Chih-Sheng Chen, Tien-Hao Chang

Deep Neural Networks (DNNs) have revolutionized artificial intelligence, achieving impressive results on diverse data types, including images, videos, and texts. However, DNNs still lag behind Gradient Boosting Decision Trees (GBDT) on tabular data, a format extensively utilized across various domains. This paper introduces DOFEN, which stands for Deep Oblivious Forest ENsemble. DOFEN is a novel DNN architecture inspired by oblivious decision trees and achieves on-off sparse selection of columns. DOFEN surpasses other DNNs on tabular data, achieving state-of-the-art performance on the well-recognized benchmark: Tabular Benchmark, which includes 73 total datasets spanning a wide array of domains. The code of DOFEN is available at: https://github.com/Sinopac-Digital-Technology-Division/DOFEN

Language

Andrew Estornell, Yang Liu

The flexible and generalized nature of large language models has allowed for their application in a wide array of language-based domains.Much like their human contemporaries, these models are capable of engaging in discussions and debates as a means of improving answer quality.We first take a theoretical approach to analyzing debate and provide a framework through which debate can be mathematically examined.Building on this framework, we provide several theoretical results for multi-agent debate.In particular, we demonstrate that similar model capabilities, or similar model responses, can result in static debate dynamics where the debate procedure simply converges to the majority opinion. When this majority opinion is the result of a common misconception (ingrained in the models through shared training data) debate is likely to converge to answers associated with that common misconception.Using insights from our theoretical results we then propose three interventions which improve the efficacy of debate. For each intervention, we provide theoretical results demonstrating how debate is improved.We also demonstrate that these interventions result in better performance on four common benchmark tasks.

Miscellaneous Aspects of Machine Learning · Supervised Learning

David Holzmüller, Leo Grinsztajn, Ingo Steinwart

For classification and regression on tabular data, the dominance of gradient-boosted decision trees (GBDTs) has recently been challenged by often much slower deep learning methods with extensive hyperparameter tuning. We address this discrepancy by introducing (a) RealMLP, an improved multilayer perceptron (MLP), and (b) strong meta-tuned default parameters for GBDTs and RealMLP. We tune RealMLP and the default parameters on a meta-train benchmark with 118 datasets and compare them to hyperparameter-optimized versions on a disjoint meta-test benchmark with 90 datasets, as well as the GBDT-friendly benchmark by Grinsztajn et al. (2022). Our benchmark results on medium-to-large tabular datasets (1K--500K samples) show that RealMLP offers a favorable time-accuracy tradeoff compared to other neural baselines and is competitive with GBDTs in terms of benchmark scores. Moreover, a combination of RealMLP and GBDTs with improved default parameters can achieve excellent results without hyperparameter tuning. Finally, we demonstrate that some of RealMLP's improvements can also considerably improve the performance of TabR with default parameters.

Miscellaneous Aspects of Machine Learning

Shenbao Yu, Yinghui Pan, Yifeng Zeng, Prashant Doshi, Guoquan Liu, Kim-Leng Poh, Mingwei Lin

Student cognitive modeling (SCM) is a fundamental task in intelligent education, with applications ranging from personalized learning to educational resource allocation. By exploiting students' response logs, SCM aims to predict their exercise performance as well as estimate knowledge proficiency in a subject. Data mining approaches such as matrix factorization can obtain high accuracy in predicting student performance on exercises, but the knowledge proficiency is unknown or poorly estimated. The situation is further exacerbated if only sparse interactions exist between exercises and students (or knowledge concepts). To solve this dilemma, we root monotonicity (a fundamental psychometric theory on educational assessments) in a co-factorization framework and present an autoencoder-like nonnegative matrix co-factorization (AE-NMCF), which improves the accuracy of estimating the student's knowledge proficiency via an encoder-decoder learning pipeline. The resulting estimation problem is nonconvex with nonnegative constraints. We introduce a projected gradient method based on block coordinate descent with Lipschitz constants and guarantee the method's theoretical convergence. Experiments on several real-world data sets demonstrate the efficacy of our approach in terms of both performance prediction accuracy and knowledge estimation ability, when compared with existing student cognitive models.

Miscellaneous Aspects of Machine Learning · General Machine Learning Techniques

Feng Peiyuan, Yichen He, Guanhua Huang, Yuan Lin, Hanchong Zhang, Yuchen Zhang, Hang Li

We introduce a novel reinforcement learning framework of LLM agents named AGILE (AGent that Interacts and Learns from Environments) designed to perform complex conversational tasks with users, leveraging LLMs, memory, tools, and interactions with experts. The agent possesses capabilities beyond conversation, including reflection, tool usage, and expert consultation. We formulate the construction of such an LLM agent as a reinforcement learning (RL) problem, in which the LLM serves as the policy model. We fine-tune the LLM using labeled data of actions and the PPO algorithm. We focus on question answering and release a dataset for agents called ProductQA, comprising challenging questions in online shopping. Our extensive experiments on ProductQA, MedMCQA and HotPotQA show that AGILE agents based on 7B and 13B LLMs trained with PPO can outperform GPT-4 agents. Our ablation study highlights the indispensability of memory, tools, consultation, reflection, and reinforcement learning in achieving the agent's strong performance. Datasets and code are available at https://github.com/bytarnish/AGILE.

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Linglan Zhao, Xuerui Zhang, Ke Yan, Shouhong Ding, Weiran Huang

Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge.With the rise of powerful pre-trained models (PTMs), there is a growing interest in training incremental learning systems using these foundation models, rather than learning from scratch. Existing works often view PTMs as a strong initial point and directly apply parameter-efficient tuning (PET) in the first session for adapting to downstream tasks.In the following sessions, most methods freeze model parameters for tackling forgetting issues. However, applying PET directly to downstream data cannot fully explore the inherent knowledge in PTMs.Additionally, freezing the parameters in incremental sessions hinders models' plasticity to novel concepts not covered in the first session. To solve the above issues, we propose a Slow And Fast parameter-Efficient tuning (SAFE) framework.In particular, to inherit general knowledge from foundation models, we include a transfer loss function by measuring the correlation between the PTM and the PET-applied model.After calibrating in the first session, the slow efficient tuning parameters can capture more informative features, improving generalization to incoming classes.Moreover, to further incorporate novel concepts, we strike a balance between stability and plasticity by fixing slow efficient tuning parameters and continuously updating the fast ones.Specifically, a cross-classification loss with feature alignment is proposed to circumvent catastrophic forgetting.During inference, we introduce an entropy-based aggregation strategy to dynamically utilize the complementarity in the slow and fast learners.Extensive experiments on seven benchmark datasets verify the effectiveness of our method by significantly surpassing the state-of-the-art.

Miscellaneous Aspects of Machine Learning · General Machine Learning Techniques

Albert Tseng, Qingyao Sun, David Hou, Christopher De Sa

Post-training quantization (PTQ) reduces the memory footprint of LLMs by quantizing weights to low-precision datatypes.Since LLM inference is usually memory-bound, PTQ methods can improve inference throughput.Recent state-of-the-art PTQ approaches use vector quantization (VQ) to quantize multiple weights at once, which improves information utilization through better shaping.However, VQ requires a codebook with size exponential in the dimension.This limits current VQ-based PTQ works to low VQ dimensions ($\le 8$) that in turn limit quantization quality.Here, we introduce QTIP, which instead uses trellis coded quantization (TCQ) to achieve ultra-high-dimensional quantization. TCQ uses a stateful decoder that separates the codebook size from the bitrate and effective dimension. QTIP introduces a spectrum of lookup-only to computed lookup-free trellis codes designed for a hardware-efficient "bitshift" trellis structure; these codes achieve state-of-the-art results in both quantization quality and inference speed.

Miscellaneous Aspects of Machine Learning · General Machine Learning Techniques

Khai Nguyen, Nhat Ho

Sliced Wasserstein (SW) and Generalized Sliced Wasserstein (GSW) have been widely used in applications due to their computational and statistical scalability. However, the SW and the GSW are only defined between distributions supported on a homogeneous domain. This limitation prevents their usage in applications with heterogeneous joint distributions with marginal distributions supported on multiple different domains. Using SW and GSW directly on the joint domains cannot make a meaningful comparison since their homogeneous slicing operator, i.e., Radon Transform (RT) and Generalized Radon Transform (GRT) are not expressive enough to capture the structure of the joint supports set. To address the issue, we propose two new slicing operators, i.e., Partial Generalized Radon Transform (PGRT) and Hierarchical Hybrid Radon Transform (HHRT). In greater detail, PGRT is the generalization of Partial Radon Transform (PRT), which transforms a subset of function arguments non-linearly while HHRT is the composition of PRT and multiple domain-specific PGRT on marginal domain arguments. By using HHRT, we extend the SW into Hierarchical Hybrid Sliced Wasserstein (H2SW) distance which is designed specifically for comparing heterogeneous joint distributions. We then discuss the topological, statistical, and computational properties of H2SW. Finally, we demonstrate the favorable performance of H2SW in 3D mesh deformation, deep 3D mesh autoencoders, and datasets comparison.

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Josh Gardner, Juan Perdomo, Ludwig Schmidt

Tabular data – structured, heterogeneous, spreadsheet-style data with rows and columns – is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets and predictors in domains such as language modeling and computer vision, this transfer learning paradigm has not had similar impact in the tabular domain. In this work, we seek to narrow this gap and present TABULA-8B, a language model for tabular prediction. We define a process for extracting a large, high-quality training dataset from the TabLib corpus, proposing methods for tabular data filtering and quality control. Using the resulting dataset, which comprises over 2.1B rows from 4.2M unique tables, we fine-tune a Llama 3-8B large language model (LLM) for tabular data prediction (classification and binned regression) using a novel packing and attention scheme for tabular prediction. Through evaluation across a test suite of 329 datasets, we find that TABULA-8B has zero-shot accuracy on unseen tables that is over 15 percentage points (pp) higher than random guessing, a feat that is not possible with existing state-of-the-art tabular prediction models (e.g. XGBoost, TabPFN). In the few-shot setting (1-32 shots), without any fine-tuning on the target datasets, TABULA-8B is 5-15 pp more accurate than XGBoost and TabPFN models that are explicitly trained on equal, or even up to 16× more data. We release our model, code, and data along with the publication of this paper.

Language · Knowledge

André F. Cruz, Moritz Hardt, Celestine Mendler-Dünner

Current question-answering benchmarks predominantly focus on accuracy in realizable prediction tasks.Conditioned on a question and answer-key, does the most likely token match the ground truth?Such benchmarks necessarily fail to evaluate LLMs' ability to quantify ground-truth outcome uncertainty.In this work, we focus on the use of LLMs as risk scores for unrealizable prediction tasks.We introduce folktexts, a software package to systematically generate risk scores using LLMs, and evaluate them against US Census data products.A flexible API enables the use of different prompting schemes, local or web-hosted models, and diverse census columns that can be used to compose custom prediction tasks.We evaluate 17 recent LLMs across five proposed benchmark tasks.We find that zero-shot risk scores produced by multiple-choice question-answering have high predictive signal but are widely miscalibrated.Base models consistently overestimate outcome uncertainty, while instruction-tuned models underestimate uncertainty and produce over-confident risk scores.In fact, instruction-tuning polarizes answer distribution regardless of true underlying data uncertainty.This reveals a general inability of instruction-tuned models to express data uncertainty using multiple-choice answers.A separate experiment using verbalized chat-style risk queries yields substantially improved calibration across instruction-tuned models.These differences in ability to quantify data uncertainty cannot be revealed in realizable settings, and highlight a blind-spot in the current evaluation ecosystem that folktexts covers.

Miscellaneous Aspects of Machine Learning · Unsupervised and Semi-supervised Learning

Wenhao Wang, Adam Dziedzic, Michael Backes, Franziska Boenisch

Recent work on studying memorization in self-supervised learning (SSL) suggests that even though SSL encoders are trained on millions of images, they still memorize individual data points. While effort has been put into characterizing the memorized data and linking encoder memorization to downstream utility, little is known about where the memorization happens inside SSL encoders. To close this gap, we propose two metrics for localizing memorization in SSL encoders on a per-layer (LayerMem) and per-unit basis (UnitMem). Our localization methods are independent of the downstream task, do not require any label information, and can be performed in a forward pass. By localizing memorization in various encoder architectures (convolutional and transformer-based) trained on diverse datasets with contrastive and non-contrastive SSL frameworks, we find that (1) while SSL memorization increases with layer depth, highly memorizing units are distributed across the entire encoder, (2) a significant fraction of units in SSL encoders experiences surprisingly high memorization of individual data points, which is in contrast to models trained under supervision, (3) atypical (or outlier) data points cause much higher layer and unit memorization than standard data points, and (4) in vision transformers, most memorization happens in the fully-connected layers. Finally, we show that localizing memorization in SSL has the potential to improve fine-tuning and to inform pruning strategies.

Miscellaneous Aspects of Machine Learning · Unsupervised and Semi-supervised Learning

Roel Bouman, Zaharah Bukhsh, Tom Heskes

In this study we evaluate 33 unsupervised anomaly detection algorithms on 52 real-world multivariate tabular data sets, performing the largest comparison of unsupervised anomaly detection algorithms to date. On this collection of data sets, the EIF (Extended Isolation Forest) algorithm significantly outperforms the most other algorithms. Visualizing and then clustering the relative performance of the considered algorithms on all data sets, we identify two clear clusters: one with "local'' data sets, and another with "global'' data sets. "Local'' anomalies occupy a region with low density when compared to nearby samples, while "global'' occupy an overall low density region in the feature space. On the local data sets the $k$NN ($k$-nearest neighbor) algorithm comes out on top. On the global data sets, the EIF (extended isolation forest) algorithm performs the best. Also taking into consideration the algorithms' computational complexity, a toolbox with these two unsupervised anomaly detection algorithms suffices for finding anomalies in this representative collection of multivariate data sets. By providing access to code and data sets, our study can be easily reproduced and extended with more algorithms and/or data sets.

Miscellaneous Aspects of Machine Learning · Kernel methods

Aleksandr Talitckii, Brendon Colbert, Matthew Peet

The accuracy and complexity of machine learning algorithms based on kernel optimization are determined by the set of kernels over which they are able to optimize. An ideal set of kernels should: admit a linear parameterization (for tractability); be dense in the set of all kernels (for robustness); be universal (for accuracy). Recently, a framework was proposed for using positive matrices to parameterize a class of positive semi-separable kernels. Although this class can be shown to meet all three criteria, previous algorithms for optimization of such kernels were limited to classification and furthermore relied on computationally complex Semidefinite Programming (SDP) algorithms. In this paper, we pose the problem of learning semiseparable kernels as a minimax optimization problem and propose a SVD-QCQP primal-dual algorithm which dramatically reduces the computational complexity as compared with previous SDP-based approaches. Furthermore, we provide an efficient implementation of this algorithm for both classification and regression -- an implementation which enables us to solve problems with 100 features and up to 30,000 datums. Finally, when applied to benchmark data, the algorithm demonstrates the potential for significant improvement in accuracy over typical (but non-convex) approaches such as Neural Nets and Random Forest with similar or better computation time.

Generative Models · Misc

Hung Le, Doyen Sahoo, Yingbo Zhou, Caiming Xiong, Silvio Savarese

Large language models (LLMs) for code are typically trained to align with natural language instructions to closely follow their intentions and requirements. However, in many practical scenarios, it becomes increasingly challenging for these models to navigate the intricate boundary between helpfulness and safety, especially against highly complex yet potentially malicious instructions. In this work, we introduce INDICT: a new framework that empowers LLMs with Internal Dialogues of Critiques for both safety and helpfulness guidance. The internal dialogue is a dual cooperative system between a safety-driven critic and a helpfulness-driven critic. Each critic provides analysis against the given task and corresponding generated response, equipped with external knowledge queried through relevant code snippets and tools like web search and code interpreter. We engage the dual critic system in both code generation stage as well as code execution stage, providing preemptive and post-hoc guidance respectively to LLMs. We evaluated INDICT on 8 diverse tasks across 8 programming languages from 5 benchmarks, using LLMs from 7B to 70B parameters. We observed that our approach can provide an advanced level of critiques of both safety and helpfulness analysis, significantly improving the quality of output codes (+10% absolute improvements in all models).

Miscellaneous Aspects of Machine Learning · Kernel methods

Benjamin Hoover, Duen Horng Chau, Hendrik Strobelt, Parikshit Ram, Dmitry Krotov

Dense Associative Memories are high storage capacity variants of the Hopfield networks that are capable of storing a large number of memory patterns in the weights of the network of a given size. Their common formulations typically require storing each pattern in a separate set of synaptic weights, which leads to the increase of the number of synaptic weights when new patterns are introduced. In this work we propose an alternative formulation of this class of models using random features, commonly used in kernel methods. In this formulation the number of network's parameters remains fixed. At the same time, new memories can be added to the network by modifying existing weights. We show that this novel network closely approximates the energy function and dynamics of conventional Dense Associative Memories and shares their desirable computational properties.

Miscellaneous Aspects of Machine Learning · Unsupervised and Semi-supervised Learning

Abhishek Kaul, Hongjin Zhang, Konstantinos Tsampourakis, George Michailidis

We consider the problem of constructing asymptotically valid confidence intervals for the change point in a high-dimensional covariance shift setting. A novel estimator for the change point parameter is developed, and its asymptotic distribution under high dimensional scaling obtained. We establish that the proposed estimator exhibits a sharp $O_p(\psi^{-2})$ rate of convergence, wherein $\psi$ represents the jump size between model parameters before and after the change point. Further, the form of the asymptotic distributions under both a vanishing and a non-vanishing regime of the jump size are characterized. In the former case, it corresponds to the argmax of an asymmetric Brownian motion, while in the latter case to the argmax of an asymmetric random walk. We then obtain the relationship between these distributions, which allows construction of regime (vanishing vs non-vanishing) adaptive confidence intervals. Easy to implement algorithms for the proposed methodology are developed and their performance illustrated on synthetic and real data sets.

Miscellaneous Aspects of Machine Learning · Unsupervised and Semi-supervised Learning

Adam B Kashlak, Prachi Loliencar, Giseon Heo

The Hidden Markov Model is a classic modelling tool with a wide swath of applications. Its inception considered observations restricted to a finite alphabet, but it was quickly extended to multivariate continuous distributions. In this article, we further extend the Hidden Markov Model from mixtures of normal distributions in $d$-dimensional Euclidean space to general Gaussian measure mixtures in locally convex topological spaces, and hence, we christen this method the Topological Hidden Markov Model. The main innovation is the use of the Onsager-Machlup functional as a proxy for the probability density function in infinite dimensional spaces. This allows for choice of a Cameron-Martin space suitable for a given application. We demonstrate the versatility of this methodology by applying it to simulated diffusion processes such as Brownian and fractional Brownian sample paths as well as the Ornstein-Uhlenbeck process. Our methodology is applied to the identification of sleep states from overnight polysomnography time series data with the aim of diagnosing Obstructive Sleep Apnea in pediatric patients. It is also applied to a series of annual cumulative snowfall curves from 1940 to 1990 in the city of Edmonton, Alberta.

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Akshay Mehra, Yunbei Zhang, Jihun Hamm

The growing popularity of transfer learning due to the availability of models pre-trained on vast amounts of data, makes it imperative to understand when the knowledge of these pre-trained models can be transferred to obtain high-performing models on downstream target tasks. However, the exact conditions under which transfer learning succeeds in a cross-domain cross-task setting are still poorly understood. To bridge this gap, we propose a novel analysis that analyzes the transferability of the representations of pre-trained models to downstream tasks in terms of their relatedness to a given reference task. Our analysis leads to an upper bound on transferability in terms of task-relatedness, quantified using the difference between the class priors, label sets, and features of the two tasks.Our experiments using state-of-the-art pre-trained models show the effectiveness of task-relatedness in explaining transferability on various vision and language tasks. The efficient computability of task-relatedness even without labels of the target task and its high correlation with the model's accuracy after end-to-end fine-tuning on the target task makes it a useful metric for transferability estimation. Our empirical results of using task-relatedness on the problem of selecting the best pre-trained model from a model zoo for a target task highlight its utility for practical problems.

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Haochen Li, Rui Zhang, Hantao Yao, Xin Zhang, Yifan Hao, Xinkai Song, Xiaqing Li, Yongwei Zhao, Yunji Chen, Ling Li

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain.As the visual-language models (VLMs) can provide essential general knowledge on unseen images, freezing the visual encoder and inserting a domain-agnostic adapter can learn domain-invariant knowledge for DAOD.However, the domain-agnostic adapter is inevitably biased to the source domain.It discards some beneficial knowledge discriminative on the unlabelled domain, \ie domain-specific knowledge of the target domain.To solve the issue, we propose a novel Domain-Aware Adapter (DA-Ada) tailored for the DAOD task.The key point is exploiting domain-specific knowledge between the essential general knowledge and domain-invariant knowledge.DA-Ada consists of the Domain-Invariant Adapter (DIA) for learning domain-invariant knowledge and the Domain-Specific Adapter (DSA) for injecting the domain-specific knowledge from the information discarded by the visual encoder.Comprehensive experiments over multiple DAOD tasks show that DA-Ada can efficiently infer a domain-aware visual encoder for boosting domain adaptive object detection.Our code is available at https://github.com/Therock90421/DA-Ada.

Miscellaneous Aspects of Machine Learning · Transfer, Multitask and Meta-learning

Hongduan Tian, Feng Liu, Zhanke Zhou, Tongliang Liu, Chengqi Zhang, Bo Han

In _cross-domain few-shot classification_ (CFC), recent works mainly focus on adapting a simple transformation head on top of a frozen pre-trained backbone with few labeled data to project embeddings into a task-specific metric space where classification can be performed by measuring similarities between image instance and prototype representations. Technically, an _assumption_ implicitly adopted in such a framework is that the prototype and image instance embeddings share the same representation transformation. However, in this paper, we find that there naturally exists a gap, which resembles the modality gap, between the prototype and image instance embeddings extracted from the frozen pre-trained backbone, and simply applying the same transformation during the adaptation phase constrains exploring the optimal representation distributions and shrinks the gap between prototype and image representations. To solve this problem, we propose a simple yet effective method, _contrastive prototype-image adaptation_ (CoPA), to adapt different transformations for prototypes and images similarly to CLIP by treating prototypes as text prompts. Extensive experiments on Meta-Dataset demonstrate that CoPA achieves the _state-of-the-art_ performance more efficiently. Meanwhile, further analyses also indicate that CoPA can learn better representation clusters, enlarge the gap, and achieve the minimum validation loss at the enlarged gap.