18
Stack Exchange
votes

Complexity of the homomorphism problem parameterized by treewidth

Posted on 6/2/2016
UQ ID:20
Science
Theoretical Computer Science
Original

The homomorphism problem for two classes and of graphs is defined as follows:

Input: a graph in , a graph in

Output: decide if there is a homomorphism from to , i.e., a mapping from the vertices of to those of such that, for any edge of , is an edge of .

For each , I will call the class of the graphs of treewidth at most . I'm interested in the problem , which I see as a parameterized problem (by the treewidth bound ). My question is: what is the complexity of this parameterized problem? Is it known to be FPT? or is it W[1]-hard?

Here are some things that I found about the problem, but which do not help me answer the question. (I write for the class of all graphs.)

Keywords & Tags
graph-algorithms
parameterized-complexity
treewidth
fixed-parameter-tractable
homomorphism
Model Answers (9)
Submitted answers from various AI models
Unsolved
No reviews yet

K2-Think

Pending UQ Validation
Needs Human Verification
MBZUAI-IFM
Qwen2.5-32B
Sep 18, 2025, 01:50 PM

The problem of determining the existence of a homomorphism from a graph ( G ) to a graph ( H ), where both ( G ) and ( H ) have treewidth at most ( k ), parameterized by ( k ), is known to be W[1]-hard.

Key Reasoning:

  1. Problem Definition: The homomorphism problem ( \text{Hom}(T_k, T_k) ) asks whether there exists a mapping ( h: V(G) \to V(H) ) preserving edges, given (...
0 model reviews
0 human reviews
No reviews yet

GPT-5

Failed UQ Validation
Needs Human Verification
OpenAI
Sep 2, 2025, 06:56 AM

Short answer: Hom(Tk, Tk) is W[1]-hard (indeed W[1]-complete) when parameterized by k. In particular, although for every fixed k the problem is solvable in polynomial time (XP), there is no f(k)·nO(1)-time algorithm unless FPT = W[1]. Moreover, under ETH there are matching lower bounds ruling out substantially faster FPT runtimes.

Why W[1]-hard

  • A convenient source of hardness is Partitioned (a....
0 model reviews
0 human reviews
No reviews yet

o4 mini

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Below is what is known (and not known) about the two‐sided tree–width–parameterized homomorphism problem

Input:  two graphs G,H with tw(G)≤k and tw(H)≤k  
Parameter:  k  
Question:  is there a homomorphism h:V(G)→V(H)?
  1. A trivial XP–algorithm.
    – First run Bodlaender’s FPT‐algorithm to find (nice) tree‐decompositions of G and of H in time f₁(k)·(|G|+|H|).
    – Then do...
0 model reviews
0 human reviews
1.0/5
(1 review)

Gemini 2.5 Pro

UQ Validated
Failed Human Verification
Google
Aug 1, 2025, 12:00 AM

Excellent question. This is a classic problem in parameterized complexity that sits at the intersection of structural graph theory and logic.

The short answer is: The problem is W[1]-hard, parameterized by .

Let's break down why this is the case, building on the results you've already found.

The XP Upper Bound

You correctly found the result...

0 model reviews
1 human reviews
No reviews yet

o3 Pro

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

Let

 p–HOM(Τk , Τk ) = {(G , H , k) | tw(G) ≤ k , tw(H) ≤ k , there is a graph–homomorphism h : G → H }

and take k to be the parameter.
We show that p–HOM(Τk , Τk ) is fixed–parameter tractable (FPT).
In fact one can decide the existence of the homomorphism in

 f(k) · (|V(G)| + |V(H)|)ᴼ(1) time,

with f(k) = (k+1)^{(k+1)²}.
Thus the problem is in FPT and (unless FPT = W[1]) it ...

0 model reviews
0 human reviews
No reviews yet

DeepSeek R1

Failed UQ Validation
Needs Human Verification
DeepSeek
deepseek-ai/DeepSeek-R1
Aug 1, 2025, 12:00 AM
<think> We are considering the problem Hom(𝒯_k, 𝒯_k) parameterized by k, where 𝒯_k is the class of graphs with treewidth at most k. The question is whether this problem is fixed-parameter tractable (FPT) or W[1]-hard.

Recall that FPT means that the problem can be solved in time f(k) * poly(n) for some computable function f, where n is the input size.

From the provided references and known res...

0 model reviews
0 human reviews
No reviews yet

o3

Failed UQ Validation
Needs Human Verification
OpenAI
Aug 1, 2025, 12:00 AM

The problem

p -HOM(𝒯k ,𝒯k )
Input : two graphs G,H with tw(G)≤k and tw(H)≤k
Parameter : k
Question : is there a homomorphism h : V(G)→V(H) ?

is fixed-parameter tractable. A simple dynamic–programming procedure that works simultaneously on tree–decompositions of G and H gives a running time of the form

  f(k)·(|V(G)|+|V(H)|)O(1) ,

hence FPT. Below is a concrete algorithm and a sho...

0 model reviews
0 human reviews
No reviews yet

Claude 3.7 Sonnet

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

Complexity of the Homomorphism Problem Parameterized by Treewidth

This question asks about the parameterized complexity of the graph homomorphism problem where both the source and target graphs have bounded treewidth.

Analysis of the Problem

The homomorphism problem asks: given graphs and , both with treewidth at most , does there exist ...

0 model reviews
0 human reviews
No reviews yet

Claude Opus 4

Failed UQ Validation
Needs Human Verification
Anthropic
Aug 1, 2025, 12:00 AM

This is an excellent question about the parameterized complexity of the graph homomorphism problem when both the source and target graphs have bounded treewidth.

The Answer

The problem parameterized by is W[1]-hard.

Key Results

The W[1]-hardness was established by Marx in his paper "Can You Beat Treewidth?" (FOCS 2007, Theory of Computin...

0 model reviews
0 human reviews
Submit Your Model's Answer
Your submission will be validated by our LLM validator and then by human experts

You need to be logged in to submit an answer