9 accepted papers
Large Language Models (LLMs) have demonstrated significant potential across various domains. However, they often struggle with integrating external knowledge and performing complex reasoning, leading to hallucinations and unreliable outputs. Retrieval Augmented Generation (RAG) has emerged as a prom
Relational deep learning (RDL) converts relational databases (RDBs) into heterogeneous graphs, but graphs derived directly from database schemas are often not well suited for how graph neural networks (GNNs) perform relational reasoning. We study what makes a relational graph suitable for deep learn…
Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, GNNs lack the inherent semantic understanding capability of rich textual node attributes, limiting their effectiveness in applications. On the other hand, we empirically observe that for ex
In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks. Agents need to solve these tasks end-to-end by interacting with an execution environment. This benchmark contains DAEval, a dataset consisting of 603 data ana…
We investigate graph neural networks on graphs with heterophily. Some existing methods amplify a node’s neighborhood with multi-hop neighbors to include more nodes with homophily. However, it is a significant challenge to set personalized neighborhood sizes for different nodes. Further, for other ho…
Tensor decompositions are regarded as a powerful tool for multidimensional signal processing. In this contribution, we focus on the well-known Canonical Polyadic (CP) decomposition and present a first-order perturbation analysis of the SEmi-algebraic framework for approximate CP decompositions via S…
This paper presents a new perspective of beamforming designs in Coordinated Multi-Point (CoMP) downlink systems that are combined with multicast schemes. The beamformer computation is expressed as a joint matrix transformation that can be regarded as an extension of the "Sequentially Drilled" Joint…
In the context of Maximum Likelihood (ML) source separation in a semi-blind scenario, where the spectra of the sources are known and distinct, the likelihood equations amount to a set of matrix decompositions (known as the "Sequentially Drilled" Joint Congruence Transformation (SeDJoCo)). However, q…
In this contribution we propose two new designs of transmit and receive processing for multi-user multiple-input-multiple-output (MIMO) downlink systems that employ filter bank based multicarrier with offset quadrature amplitude modulation (FBMC/OQAM). Our goal is to overcome the limits on the chann…