19 accepted papers
While deep generative models have significantly advanced representation learning, they may inherit or amplify biases and fairness issues by encoding sensitive attributes alongside predictive features. Enforcing strict independence in disentanglement is often unrealistic when target and sensitive fac
Flow Matching has limited ability in achieving one-step generation due to its reliance on learned curved trajectories. Previous studies have attempted to address this limitation by either modifying the coupling distribution to prevent interpolant intersections or introducing consistency and mean-vel
Dynamic graph neural networks (dynamic GNNs) have demonstrated remarkable effectiveness in analyzing time-varying graph-structured data. However, their black-box nature often hinders users from understanding their predictions, which can limit their applications. In recent years, there has been a sur
Explicit noise-level conditioning is widely regarded as essential for the effective operation of Graph Diffusion Models (GDMs). In this work, we challenge this assumption by investigating whether denoisers can implicitly infer noise levels directly from corrupted graph structures, potentially elimin…
Finding specific preference-guided Pareto solutions that represent different trade-offs among multiple objectives is critical yet challenging in multi-objective problems. Existing methods are restrictive in preference definitions and/or their theoretical guarantees. In this work, we introduce a Fle…
Machine learning over graphs has recently attracted growing attention due to its ability to analyze and learn complex relations within critical interconnected systems. However, the disparate impact that is amplified by the use of biased graph structures in these algorithms has raised significant con…
Conformal prediction is an uncertainty quantification method that constructs a prediction set for a previously unseen datum, ensuring the true label is included with a predetermined coverage probability. Adaptive conformal prediction has been developed to address data distribution shifts in dynamic…
Federated learning is renowned for its efficacy in distributed model training, ensuring that users, called clients, retain data privacy by not disclosing their data to the central server that orchestrates collaborations. Most previous work on federated learning assumes that clients possess static ba…
Many real-world networks such as social networks, traffic networks vary over time, which can be modeled as dynamic graphs. Despite the significant number of systems that can facilitate from the algorithmic tools over dynamic graphs, dynamic graph representation learning is an under-explored research…
Selective sampling is an online learning framework where the learner tries to detect the data samples whose labels can boost the performance maximally, and only the labels of chosen data samples are queried. While the design of selective sampling algorithms is extensively studied for independent dat…
Online learning with expert advice is widely used in various machine learning tasks. It considers the problem where a learner chooses one from a set of experts to take advice and make a decision. In many learning problems, experts may be related, henceforth the learner can observe the losses associa…
Multi-kernel learning (MKL) exhibits well-documented performance in online non-linear function approximation. Federated learning enables a group of learners (called clients) to train an MKL model on the data distributed among clients to perform online non-linear function approximation. There are som…
With complex systems emerging in various applications, e.g., financial, biological and social networks, graphs become working horse to model and analyse these systems. Nodes within networks usually entail attributes. Due to privacy concerns and missing observations, nodal attributes may be unavailab…
Combining benefits of kernels with Bayesian models, Gaussian process (GP) based approaches have well-documented merits not only in learning over a rich class of nonlinear functions, but also quantifying the associated uncertainty. While most GP approaches rely on a single preselected prior, the pres…
Multi-kernel learning (MKL) exhibits reliable performance in nonlinear function approximation tasks. Instead of using one kernel, it learns the optimal kernel from a pre-selected dictionary of kernels. The selection of the dictionary has crucial impact on both the performance and complexity of MKL.…
Kernel-based methods exhibit well-documented performance in various nonlinear learning tasks. Most of them rely on a preselected kernel, whose prudent choice presumes task-specific prior information. To cope with this limitation, multi-kernel learning has gained popularity thanks to its flexibility…
Kernel-based methods have well-appreciated performance in various nonlinear learning tasks. Most of them rely on a preselected kernel, whose prudent choice presumes task-specific prior information. To cope with this limitation, multi-kernel learning has gained popularity thanks to its flexibility in…
Linear structural vector autoregressive models constitute a generalization of structural equation models (SEMs) and vector autoregressive (VAR) models, two popular approaches for topology inference of directed graphs. Although simple and tractable, linear SVARMs seldom capture nonlinearities that ar…
In this paper, we study the problem of sparse signal recovery when partial but partly erroneous prior knowledge of the signal's support is available. Based on the conventional sparse Bayesian learning framework, we propose an improved hierarchical prior model. The proposed modeling constitutes a thr…